all | dynamic | editing | fast | generalization | human | video | lighting | reconstruction | texture | semantic | pose-slam | others
- iLabel: Revealing Objects in Neural Fields, RAL2022 | [code]
A neural field trained with self-supervision to efficiently represent the geometry and colour of a 3D scene tends to automatically decompose it into coherent and accurate object-like regions, which can be revealed with sparse labelling interactions to produce a 3D semantic scene segmentation. Our real-time iLabel system takes input from a hand-held RGB-D camera, requires zero prior training data, and works in an ‘open set’ manner, with semantic classes defined on the fly by the user. iLabel's underlying model is a simple multilayer perceptron (MLP), trained from scratch to learn a neural representation of a single 3D scene. The model is updated continually and visualised in real-time, allowing the user to focus interactions to achieve extremely efficient semantic segmentation. A room-scale scene can be accurately labelled into 10+ semantic categories with around 100 clicks, taking less than 5 minutes. Quantitative labelling accuracy scales powerfully with the number of clicks, and rapidly surpasses standard pre-trained semantic segmentation methods. We also demonstrate a hierarchical labelling variant of iLabel and a ‘hands-free’ mode where the user only needs to supply label names for automatically-generated locations.
- NeRF-RPN: A general framework for object detection in NeRFs | [code]
This paper presents the first significant object detection framework, NeRF-RPN, which directly operates on NeRF. Given a pre-trained NeRF model, NeRF-RPN aims to detect all bounding boxes of objects in a scene. By exploiting a novel voxel representation that incorporates multi-scale 3D neural volumetric features, we demonstrate it is possible to regress the 3D bounding boxes of objects in NeRF directly without rendering the NeRF at any viewpoint. NeRF-RPN is a general framework and can be applied to detect objects without class labels. We experimented the NeRF-RPN with various backbone architectures, RPN head designs and loss functions. All of them can be trained in an end-to-end manner to estimate high quality 3D bounding boxes. To facilitate future research in object detection for NeRF, we built a new benchmark dataset which consists of both synthetic and real-world data with careful labeling and clean up. Please click this https URL for visualizing the 3D region proposals by our NeRF-RPN. Code and dataset will be made available.
- SegNeRF: 3D Part Segmentation with Neural Radiance Fields | [code]
Recent advances in Neural Radiance Fields (NeRF) boast impressive performances for generative tasks such as novel view synthesis and 3D reconstruction. Methods based on neural radiance fields are able to represent the 3D world implicitly by relying exclusively on posed images. Yet, they have seldom been explored in the realm of discriminative tasks such as 3D part segmentation. In this work, we attempt to bridge that gap by proposing SegNeRF: a neural field representation that integrates a semantic field along with the usual radiance field. SegNeRF inherits from previous works the ability to perform novel view synthesis and 3D reconstruction, and enables 3D part segmentation from a few images. Our extensive experiments on PartNet show that SegNeRF is capable of simultaneously predicting geometry, appearance, and semantic information from posed images, even for unseen objects. The predicted semantic fields allow SegNeRF to achieve an average mIoU of 30.30% for 2D novel view segmentation, and 37.46% for 3D part segmentation, boasting competitive performance against point-based methods by using only a few posed images. Additionally, SegNeRF is able to generate an explicit 3D model from a single image of an object taken in the wild, with its corresponding part segmentation.
- CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory | [code]
We propose CLIP-Fields, an implicit scene model that can be trained with no direct human supervision. This model learns a mapping from spatial locations to semantic embedding vectors. The mapping can then be used for a variety of tasks, such as segmentation, instance identification, semantic search over space, and view localization. Most importantly, the mapping can be trained with supervision coming only from web-image and web-text trained models such as CLIP, Detic, and Sentence-BERT. When compared to baselines like Mask-RCNN, our method outperforms on few-shot instance identification or semantic segmentation on the HM3D dataset with only a fraction of the examples. Finally, we show that using CLIP-Fields as a scene memory, robots can perform semantic navigation in real-world environments. Our code and demonstrations are available here: https://mahis.life/clip-fields/
- ViewFool: Evaluating the Robustness of Visual Recognition to Adversarial Viewpoints, NeurIPS2022 | [code]
Recent studies have demonstrated that visual recognition models lack robustness to distribution shift. However, current work mainly considers model robustness to 2D image transformations, leaving viewpoint changes in the 3D world less explored. In general, viewpoint changes are prevalent in various real-world applications (e.g., autonomous driving), making it imperative to evaluate viewpoint robustness. In this paper, we propose a novel method called ViewFool to find adversarial viewpoints that mislead visual recognition models. By encoding real-world objects as neural radiance fields (NeRF), ViewFool characterizes a distribution of diverse adversarial viewpoints under an entropic regularizer, which helps to handle the fluctuations of the real camera pose and mitigate the reality gap between the real objects and their neural representations. Experiments validate that the common image classifiers are extremely vulnerable to the generated adversarial viewpoints, which also exhibit high cross-model transferability. Based on ViewFool, we introduce ImageNet-V, a new out-of-distribution dataset for benchmarking viewpoint robustness of image classifiers. Evaluation results on 40 classifiers with diverse architectures, objective functions, and data augmentations reveal a significant drop in model performance when tested on ImageNet-V, which provides a possibility to leverage ViewFool as an effective data augmentation strategy to improve viewpoint robustness.
- A Simple Plugin for Transforming Images to Arbitrary Scales | [code]
Existing models on super-resolution often specialized for one scale, fundamentally limiting their use in practical scenarios. In this paper, we aim to develop a general plugin that can be inserted into existing super-resolution models, conveniently augmenting their ability towards Arbitrary Resolution Image Scaling, thus termed ARIS. We make the following contributions: (i) we propose a transformer-based plugin module, which uses spatial coordinates as query, iteratively attend the low-resolution image feature through cross-attention, and output visual feature for the queried spatial location, resembling an implicit representation for images; (ii) we introduce a novel self-supervised training scheme, that exploits consistency constraints to effectively augment the model's ability for upsampling images towards unseen scales, i.e. ground-truth high-resolution images are not available; (iii) without loss of generality, we inject the proposed ARIS plugin module into several existing models, namely, IPT, SwinIR, and HAT, showing that the resulting models can not only maintain their original performance on fixed scale factor but also extrapolate to unseen scales, substantially outperforming existing any-scale super-resolution models on standard benchmarks, e.g. Urban100, DIV2K, etc.
- Feature-Realistic Neural Fusion for Real-Time, Open Set Scene Understanding | [code]
General scene understanding for robotics requires flexible semantic representation, so that novel objects and structures which may not have been known at training time can be identified, segmented and grouped. We present an algorithm which fuses general learned features from a standard pre-trained network into a highly efficient 3D geometric neural field representation during real-time SLAM. The fused 3D feature maps inherit the coherence of the neural field's geometry representation. This means that tiny amounts of human labelling interacting at runtime enable objects or even parts of objects to be robustly and accurately segmented in an open set manner.
- Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence, NeurIPS2022 |
[code]Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters. This architecture, however, inevitably results in a low-resolution matching field that additionally requires an ad-hoc interpolation process as a post-processing for converting it into a high-resolution one, certainly limiting the overall performance of matching results. To overcome this, inspired by recent success of implicit neural representation, we present a novel method for semantic correspondence, called Neural Matching Field (NeMF). However, complicacy and high-dimensionality of a 4D matching field are the major hindrances, which we propose a cost embedding network to process a coarse cost volume to use as a guidance for establishing high-precision matching field through the following fully-connected network. Nevertheless, learning a high-dimensional matching field remains challenging mainly due to computational complexity, since a naive exhaustive inference would require querying from all pixels in the 4D space to infer pixel-wise correspondences. To overcome this, we propose adequate training and inference procedures, which in the training phase, we randomly sample matching candidates and in the inference phase, we iteratively performs PatchMatch-based inference and coordinate optimization at test time. With these combined, competitive results are attained on several standard benchmarks for semantic correspondence. Code and pre-trained weights are available at this https URL.
- Understanding Pure CLIP Guidance for Voxel Grid NeRF Models | [code]
We explore the task of text to 3D object generation using CLIP. Specifically, we use CLIP for guidance without access to any datasets, a setting we refer to as pure CLIP guidance. While prior work has adopted this setting, there is no systematic study of mechanics for preventing adversarial generations within CLIP. We illustrate how different image-based augmentations prevent the adversarial generation problem, and how the generated results are impacted. We test different CLIP model architectures and show that ensembling different models for guidance can prevent adversarial generations within bigger models and generate sharper results. Furthermore, we implement an implicit voxel grid model to show how neural networks provide an additional layer of regularization, resulting in better geometrical structure and coherency of generated objects. Compared to prior work, we achieve more coherent results with higher memory efficiency and faster training speeds.
- City-scale Incremental Neural Mapping with Three-layer Sampling and Panoptic Representation | [code]
Neural implicit representations are drawing a lot of attention from the robotics community recently, as they are expressive, continuous and compact. However, city-scale incremental implicit dense mapping based on sparse LiDAR input is still an under-explored challenge. To this end,we successfully build the first city-scale incremental neural mapping system with a panoptic representation that consists of both environment-level and instance-level modelling. Given a stream of sparse LiDAR point cloud, it maintains a dynamic generative model that maps 3D coordinates to signed distance field (SDF) values. To address the difficulty of representing geometric information at different levels in city-scale space, we propose a tailored three-layer sampling strategy to dynamically sample the global, local and near-surface domains. Meanwhile, to realize high fidelity mapping, category-specific prior is introduced to better model the geometric details, leading to a panoptic representation. We evaluate on the public SemanticKITTI dataset and demonstrate the significance of the newly proposed three-layer sampling strategy and panoptic representation, using both quantitative and qualitative results. Codes and data will be publicly available.
- 360FusionNeRF: Panoramic Neural Radiance Fields with Joint Guidance | [code]
We present a method to synthesize novel views from a single 360∘ panorama image based on the neural radiance field (NeRF). Prior studies in a similar setting rely on the neighborhood interpolation capability of multi-layer perceptions to complete missing regions caused by occlusion, which leads to artifacts in their predictions. We propose 360FusionNeRF, a semi-supervised learning framework where we introduce geometric supervision and semantic consistency to guide the progressive training process. Firstly, the input image is re-projected to 360∘ images, and auxiliary depth maps are extracted at other camera positions. The depth supervision, in addition to the NeRF color guidance, improves the geometry of the synthesized views. Additionally, we introduce a semantic consistency loss that encourages realistic renderings of novel views. We extract these semantic features using a pre-trained visual encoder such as CLIP, a Vision Transformer trained on hundreds of millions of diverse 2D photographs mined from the web with natural language supervision. Experiments indicate that our proposed method can produce plausible completions of unobserved regions while preserving the features of the scene. When trained across various scenes, 360FusionNeRF consistently achieves the state-of-the-art performance when transferring to synthetic Structured3D dataset (PSNR
5%, SSIM3% LPIPS13%), real-world Matterport3D dataset (PSNR3%, SSIM3% LPIPS9%) and Replica360 dataset (PSNR8%, SSIM2% LPIPS~18%). - Baking in the Feature: Accelerating Volumetric Segmentation by Rendering Feature Maps | [code]
Methods have recently been proposed that densely segment 3D volumes into classes using only color images and expert supervision in the form of sparse semantically annotated pixels. While impressive, these methods still require a relatively large amount of supervision and segmenting an object can take several minutes in practice. Such systems typically only optimize their representation on the particular scene they are fitting, without leveraging any prior information from previously seen images. In this paper, we propose to use features extracted with models trained on large existing datasets to improve segmentation performance. We bake this feature representation into a Neural Radiance Field (NeRF) by volumetrically rendering feature maps and supervising on features extracted from each input image. We show that by baking this representation into the NeRF, we make the subsequent classification task much easier. Our experiments show that our method achieves higher segmentation accuracy with fewer semantic annotations than existing methods over a wide range of scenes.
- NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes |
[code]Neural volumetric representations have shown the potential that Multi-layer Perceptrons (MLPs) can be optimized with multi-view calibrated images to represent scene geometry and appearance, without explicit 3D supervision. Object segmentation can enrich many downstream applications based on the learned radiance field. However, introducing hand-crafted segmentation to define regions of interest in a complex real-world scene is non-trivial and expensive as it acquires per view annotation. This paper carries out the exploration of self-supervised learning for object segmentation using NeRF for complex real-world scenes. Our framework, called NeRF with Self-supervised Object Segmentation NeRF-SOS, couples object segmentation and neural radiance field to segment objects in any view within a scene. By proposing a novel collaborative contrastive loss in both appearance and geometry levels, NeRF-SOS encourages NeRF models to distill compact geometry-aware segmentation clusters from their density fields and the self-supervised pre-trained 2D visual features. The self-supervised object segmentation framework can be applied to various NeRF models that both lead to photo-realistic rendering results and convincing segmentation maps for both indoor and outdoor scenarios. Extensive results on the LLFF, Tank & Temple, and BlendedMVS datasets validate the effectiveness of NeRF-SOS. It consistently surpasses other 2D-based self-supervised baselines and predicts finer semantics masks than existing supervised counterparts. Please refer to the video on our project page for more details:this https URL.
- Implicit Neural Representations for Medical Imaging Segmentation, MICCAI2022 | [code]
3D signals in medical imaging, such as CT scans, are usually parameterized as a discrete grid of voxels. For instance, existing state-of-the-art organ segmentation methods learn discrete segmentation maps. Unfortunately, the memory requirements of such methods grow cubically with increasing spatial resolution, which makes them unsuitable for processing high resolution scans. To overcome this, we design an Implicit Organ Segmentation Network (IOSNet) that utilizes continuous Implicit Neural Representations and has several useful properties. Firstly, the IOSNet decoder memory is roughly constant and independent of the spatial resolution since it parameterizes the segmentation map as a continuous function. Secondly, IOSNet converges much faster than discrete voxel based methods due to its ability to accurately segment organs irrespective of organ sizes, thereby alleviating size imbalance issues without requiring any auxiliary tricks. Thirdly, IOSNet naturally supports super-resolution (i.e. sampling at arbitrary resolutions during inference) due to its continuous learnt representations. Moreover, despite using a simple lightweight decoder, IOSNet consistently outperforms the discrete specialized segmentation architecture UNet. Hence, our approach demonstrates that Implicit Neural Representations are well-suited for medical imaging applications, especially for processing high-resolution 3D medical scans.
- Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations, 3DV2022(oral) |
[code]We present Neural Feature Fusion Fields (N3F), a method that improves dense 2D image feature extractors when the latter are applied to the analysis of multiple images reconstructible as a 3D scene. Given an image feature extractor, for example pre-trained using self-supervision, N3F uses it as a teacher to learn a student network defined in 3D space. The 3D student network is similar to a neural radiance field that distills said features and can be trained with the usual differentiable rendering machinery. As a consequence, N3F is readily applicable to most neural rendering formulations, including vanilla NeRF and its extensions to complex dynamic scenes. We show that our method not only enables semantic understanding in the context of scene-specific neural fields without the use of manual labels, but also consistently improves over the self-supervised 2D baselines. This is demonstrated by considering various tasks, such as 2D object retrieval, 3D segmentation, and scene editing, in diverse sequences, including long egocentric videos in the EPIC-KITCHENS benchmark.
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation | [code]
Large text-to-image models achieved a remarkable leap in the evolution of AI, enabling high-quality and diverse synthesis of images from a given text prompt. However, these models lack the ability to mimic the appearance of subjects in a given reference set and synthesize novel renditions of them in different contexts. In this work, we present a new approach for "personalization" of text-to-image diffusion models (specializing them to users' needs). Given as input just a few images of a subject, we fine-tune a pretrained text-to-image model (Imagen, although our method is not limited to a specific model) such that it learns to bind a unique identifier with that specific subject. Once the subject is embedded in the output domain of the model, the unique identifier can then be used to synthesize fully-novel photorealistic images of the subject contextualized in different scenes. By leveraging the semantic prior embedded in the model with a new autogenous class-specific prior preservation loss, our technique enables synthesizing the subject in diverse scenes, poses, views, and lighting conditions that do not appear in the reference images. We apply our technique to several previously-unassailable tasks, including subject recontextualization, text-guided view synthesis, appearance modification, and artistic rendering (all while preserving the subject's key features). Project page: this https URL
- NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes | [code]
We present NeSF, a method for producing 3D semantic fields from pre-trained density fields and sparse 2D semantic supervision. Our method side-steps traditional scene representations by leveraging neural representations where 3D information is stored within neural fields. In spite of being supervised by 2D signals alone, our method is able to generate 3D-consistent semantic maps from novel camera poses and can be queried at arbitrary 3D points. Notably, NeSF is compatible with any method producing a density field, and its accuracy improves as the quality of the pre-trained density fields improve. Our empirical analysis demonstrates comparable quality to competitive 2D and 3D semantic segmentation baselines on convincing synthetic scenes while also offering features unavailable to existing methods.
- Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis, ICCV2021 |
[code]We present DietNeRF, a 3D neural scene representation estimated from a few images. Neural Radiance Fields (NeRF) learn a continuous volumetric representation of a scene through multi-view consistency, and can be rendered from novel viewpoints by ray casting. While NeRF has an impressive ability to reconstruct geometry and fine details given many images, up to 100 for challenging 360° scenes, it often finds a degenerate solution to its image reconstruction objective when only a few input views are available. To improve few-shot quality, we propose DietNeRF. We introduce an auxiliary semantic consistency loss that encourages realistic renderings at novel poses. DietNeRF is trained on individual scenes to (1) correctly render given input views from the same pose, and (2) match high-level semantic attributes across different, random poses. Our semantic loss allows us to supervise DietNeRF from arbitrary poses. We extract these semantics using a pre-trained visual encoder such as CLIP, a Vision Transformer trained on hundreds of millions of diverse single-view, 2D photographs mined from the web with natural language supervision. In experiments, DietNeRF improves the perceptual quality of few-shot view synthesis when learned from scratch, can render novel views with as few as one observed image when pre-trained on a multi-view dataset, and produces plausible completions of completely unobserved regions.
- Unsupervised Discovery of Object Radiance Fields, ICLR2022 | [code]
We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision. Most existing methods on scene decomposition lack one or more of these characteristics, due to the fundamental challenge in integrating the complex 3D-to-2D image formation process into powerful inference schemes like deep networks. In this paper, we propose unsupervised discovery of Object Radiance Fields (uORF), integrating recent progresses in neural 3D scene representations and rendering with deep inference networks for unsupervised 3D scene decomposition. Trained on multi-view RGB images without annotations, uORF learns to decompose complex scenes with diverse, textured background from a single image. We show that uORF performs well on unsupervised 3D scene segmentation, novel view synthesis, and scene editing on three datasets.
- In-Place Scene Labelling and Understanding with Implicit Scene Representation, ICCV2021(oral) |
[code]Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are appealing as they do not require prior training data, but the same fully self-supervised approach is not possible for semantics because labels are human-defined properties.