CVPR 2024 Papers

This paper presents a novel category agnostic model for visual rearrangement task which can help an embodied agent to physically recover the shuffled scene configuration without any category concepts to the goal configuration. Previous methods usually follow a similar architecture completing the rearrangement task by aligning the scene changes of the goal and shuffled configuration according to the semantic scene graphs. However constructing scene graphs requires the inference of category labels which not only causes the accuracy drop of the entire task but also limits the application in real world scenario. In this paper we delve deep into the essence of visual rearrangement task and focus on the two most essential issues scene change detection and scene change matching. We utilize the movement and the protrusion of point cloud to accurately identify the scene changes and match these changes depending on the similarity of category agnostic appearance feature. Moreover to assist the agent to explore the environment more efficiently and comprehensively we propose a closer-aligned-retrace exploration policy aiming to observe more details of the scene at a closer distance. We conduct extensive experiments on AI2THOR Rearrangement Challenge based on RoomR dataset and a new multi-room multi-instance dataset MrMiR collected by us. The experimental results demonstrate the effectiveness of our proposed method.

Comparing different age estimation methods poses a challenge due to the unreliability of published results stemming from inconsistencies in the benchmarking process. Previous studies have reported continuous performance improvements over the past decade using specialized methods; however our findings challenge these claims. This paper identifies two trivial yet persistent issues with the currently used evaluation protocol and describes how to resolve them. We offer an extensive comparative analysis for state-of-the-art facial age estimation methods. Surprisingly we find that the performance differences between the methods are negligible compared to the effect of other factors such as facial alignment facial coverage image resolution model architecture or the amount of data used for pretraining. We use the gained insights to propose using FaRL as the backbone model and demonstrate its effectiveness on all public datasets. We make the source code and exact data splits public on GitHub and in the supplementary material.

An important and unsolved problem in computer vision is to ensure that the algorithms are robust to changes in image domains. We address this problem in the scenario where we have access to images from the target domains but no annotations. Motivated by the challenges of the OOD-CV benchmark where we encounter real world Out-of-Domain (OOD) nuisances and occlusion we introduce a novel Bayesian approach to OOD robustness for object classification. Our work extends Compositional Neural Networks (CompNets) which have been shown to be robust to occlusion but degrade badly when tested on OOD data. We exploit the fact that CompNets contain a generative head defined over feature vectors represented by von Mises-Fisher (vMF) kernels which correspond roughly to object parts and can be learned without supervision. We obverse that some vMF kernels are similar between different domains while others are not. This enables us to learn a transitional dictionary of vMF kernels that are intermediate between the source and target domains and train the generative model on this dictionary using the annotations on the source domain followed by iterative refinement. This approach termed Unsupervised Generative Transition (UGT) performs very well in OOD scenarios even when occlusion is present. UGT is evaluated on different OOD benchmarks including the OOD-CV dataset several popular datasets (e.g. ImageNet-C artificial image corruptions (including adding occluders) and synthetic-to-real domain transfer and does well in all scenarios outperforming SOTA alternatives.

Human comprehension of a video stream is naturally broad: in a few instants we are able to understand what is happening the relevance and relationship of objects and forecast what will follow in the near future everything all at once. We believe that - to effectively transfer such an holistic perception to intelligent machines - an important role is played by learning to correlate concepts and to abstract knowledge coming from different tasks to synergistically exploit them when learning novel skills. To accomplish this we look for a unified approach to video understanding which combines shared temporal modelling of human actions with minimal overhead to support multiple downstream tasks and enable cooperation when learning novel skills. We then propose EgoPack a solution that creates a collection of task perspectives that can be carried across downstream tasks and used as a potential source of additional insights as a backpack of skills that a robot can carry around and use when needed. We demonstrate the effectiveness and efficiency of our approach on four Ego4D benchmarks outperforming current state-of-the-art methods. Project webpage: https://sapeirone.github.io/EgoPack.

Estimating the 6D object pose from a single RGB image often involves noise and indeterminacy due to challenges such as occlusions and cluttered backgrounds. Meanwhile diffusion models have shown appealing performance in generating high-quality images from random noise with high indeterminacy through step-by-step denoising. Inspired by their denoising capability we propose a novel diffusion-based framework (6D-Diff) to handle the noise and indeterminacy in object pose estimation for better performance. In our framework to establish accurate 2D-3D correspondence we formulate 2D keypoints detection as a reverse diffusion (denoising) process. To facilitate such a denoising process we design a Mixture-of-Cauchy-based forward diffusion process and condition the reverse process on the object appearance features. Extensive experiments on the LM-O and YCB-V datasets demonstrate the effectiveness of our framework.

This paper targets high-fidelity and real-time view synthesis of dynamic 3D scenes at 4K resolution. Recent methods on dynamic view synthesis have shown impressive rendering quality. However their speed is still limited when rendering high-resolution images. To overcome this problem we propose 4K4D a 4D point cloud representation that supports hardware rasterization and network pre-computation to enable unprecedented rendering speed with a high rendering quality. Our representation is built on a 4D feature grid so that the points are naturally regularized and can be robustly optimized. In addition we design a novel hybrid appearance model that significantly boosts the rendering quality while preserving efficiency. Moreover we develop a differentiable depth peeling algorithm to effectively learn the proposed model from RGB videos. Experiments show that our representation can be rendered at over 400 FPS on the DNA-Rendering dataset at 1080p resolution and 80 FPS on the ENeRF-Outdoor dataset at 4K resolution using an RTX 4090 GPU which is 30x faster than previous methods and achieves the state-of-the-art rendering quality. Our project page is available at https://zju3dv.github.io/4k4d.

Recent breakthroughs in text-to-4D generation rely on pre-trained text-to-image and text-to-video models to generate dynamic 3D scenes. However current text-to-4D methods face a three-way tradeoff between the quality of scene appearance 3D structure and motion. For example text-to-image models and their 3D-aware variants are trained on internet-scale image datasets and can be used to produce scenes with realistic appearance and 3D structure---but no motion. Text-to-video models are trained on relatively smaller video datasets and can produce scenes with motion but poorer appearance and 3D structure. While these models have complementary strengths they also have opposing weaknesses making it difficult to combine them in a way that alleviates this three-way tradeoff. Here we introduce hybrid score distillation sampling an alternating optimization procedure that blends supervision signals from multiple pre-trained diffusion models and incorporates benefits of each for high-fidelity text-to-4D generation. Using hybrid SDS we demonstrate synthesis of 4D scenes with compelling appearance 3D structure and motion.

The studies of human clothing for digital avatars have predominantly relied on synthetic datasets. While easy to collect synthetic data often fall short in realism and fail to capture authentic clothing dynamics. Addressing this gap we introduce 4D-DRESS the first real-world 4D dataset advancing human clothing research with its high-quality 4D textured scans and garment meshes. 4D-DRESS captures 64 outfits in 520 human motion sequences amounting to 78k textured scans. Creating a real-world clothing dataset is challenging particularly in annotating and segmenting the extensive and complex 4D human scans. To address this we develop a semi-automatic 4D human parsing pipeline. We efficiently combine a human-in-the-loop process with automation to accurately label 4D scans in diverse garments and body movements. Leveraging precise annotations and high-quality garment meshes we establish several benchmarks for clothing simulation and reconstruction. 4D-DRESS offers realistic and challenging data that complements synthetic sources paving the way for advancements in research of lifelike human clothing. Website: https://ait.ethz.ch/4d-dress

Representing and rendering dynamic scenes has been an important but challenging task. Especially to accurately model complex motions high efficiency is usually hard to guarantee. To achieve real-time dynamic scene rendering while also enjoying high training and storage efficiency we propose 4D Gaussian Splatting (4D-GS) as a holistic representation for dynamic scenes rather than applying 3D-GS for each individual frame. In 4D-GS a novel explicit representation containing both 3D Gaussians and 4D neural voxels is proposed. A decomposed neural voxel encoding algorithm inspired by HexPlane is proposed to efficiently build Gaussian features from 4D neural voxels and then a lightweight MLP is applied to predict Gaussian deformations at novel timestamps. Our 4D-GS method achieves real-time rendering under high resolutions 82 FPS at an 800*800 resolution on an RTX 3090 GPU while maintaining comparable or better quality than previous state-of-the-art methods. More demos and code are available at https://guanjunwu.github.io/4dgs.

3DiffTection introduces a novel method for 3D object detection from single images utilizing a 3D-aware diffusion model for feature extraction. Addressing the resource-intensive nature of annotating large-scale 3D image data our approach leverages pretrained diffusion models traditionally used for 2D tasks and adapts them for 3D detection through geometric and semantic tuning. Geometrically we enhance the model to perform view synthesis from single images incorporating an epipolar warp operator. This process utilizes easily accessible posed image data eliminating the need for manual annotation. Semantically the model is further refined on target detection data. Both stages utilize ControlNet ensuring the preservation of original feature capabilities. Through our methodology we obtain 3D-aware features that excel in identifying cross-view point correspondences. In 3D detection 3DiffTection substantially surpasses previous benchmarks e.g. Cube-RCNN by 9.43% in AP3D on the Omni3D-ARkitscene dataset. Furthermore 3DiffTection demonstrates robust label efficiency and generalizes well to cross-domain data nearly matching fully-supervised models in zero-shot scenarios.

Visual content creation has aroused a surge of interest given its applications in mobile photography and AR/VR. Portrait style transfer and 3D recovery from monocular images as two representative tasks have so far evolved independently. In this paper we make a connection between the two and tackle the challenging task of 3D portrait stylization - modeling high-fidelity 3D stylized avatars from captured 2D portrait images. However naively combining the techniques from the two isolated areas may suffer from either inadequate stylization or absence of 3D assets. To this end we propose 3DToonify a new framework that introduces a progressive training scheme to achieve 3D style adaption on spatial neural representation (SNR). SNR is constructed with implicit fields and they are dynamically optimized by the progressive training scheme which consists of three stages: guided prior learning deformable geometry adaption and explicit texture adaption. In this way stylized geometry and texture are learned in SNR in an explicit and structured way with only a single stylized exemplar needed. Moreover our method obtains style-adaptive underlying structures (i.e. deformable geometry and exaggerated texture) and view-consistent stylized avatar rendering from arbitrary novel viewpoints. Both qualitative and quantitative experiments have been conducted to demonstrate the effectiveness and superiority of our method for automatically generating exemplar-guided 3D stylized avatars.

Learning 3D scene flow from LiDAR point clouds presents significant difficulties including poor generalization from synthetic datasets to real scenes scarcity of real-world 3D labels and poor performance on real sparse LiDAR point clouds. We present a novel approach from the perspective of auto-labelling aiming to generate a large number of 3D scene flow pseudo labels for real-world LiDAR point clouds. Specifically we employ the assumption of rigid body motion to simulate potential object-level rigid movements in autonomous driving scenarios. By updating different motion attributes for multiple anchor boxes the rigid motion decomposition is obtained for the whole scene. Furthermore we developed a novel 3D scene flow data augmentation method for global and local motion. By perfectly synthesizing target point clouds based on augmented motion parameters we easily obtain lots of 3D scene flow labels in point clouds highly consistent with real scenarios. On multiple real-world datasets including LiDAR KITTI nuScenes and Argoverse our method outperforms all previous supervised and unsupervised methods without requiring manual labelling. Impressively our method achieves a tenfold reduction in EPE3D metric on the LiDAR KITTI dataset reducing it from 0.190m to a mere 0.008m error.

We propose a novel method for 3D point cloud action recognition. Understanding human actions in RGB videos has been widely studied in recent years however its 3D point cloud counterpart remains under-explored despite the clear value that 3D information may bring. This is mostly due to the inherent limitation of the point cloud data modality---lack of structure permutation invariance and varying number of points---which makes it difficult to learn a spatio-temporal representation. To address this limitation we propose the 3DinAction pipeline that first estimates patches moving in time (t-patches) as a key building block alongside a hierarchical architecture that learns an informative spatio-temporal representation. We show that our method achieves improved performance on existing datasets including DFAUST and IKEA ASM. Code is publicly available at https://github.com/sitzikbs/3dincaction

Constructing photo-realistic Free-Viewpoint Videos (FVVs) of dynamic scenes from multi-view videos remains a challenging endeavor. Despite the remarkable advancements achieved by current neural rendering techniques these methods generally require complete video sequences for offline training and are not capable of real-time rendering. To address these constraints we introduce 3DGStream a method designed for efficient FVV streaming of real-world dynamic scenes. Our method achieves fast on-the-fly per-frame reconstruction within 12 seconds and real-time rendering at 200 FPS. Specifically we utilize 3D Gaussians (3DGs) to represent the scene. Instead of the naive approach of directly optimizing 3DGs per-frame we employ a compact Neural Transformation Cache (NTC) to model the translations and rotations of 3DGs markedly reducing the training time and storage required for each FVV frame. Furthermore we propose an adaptive 3DG addition strategy to handle emerging objects in dynamic scenes. Experiments demonstrate that 3DGStream achieves competitive performance in terms of rendering speed image quality training time and model storage when compared with state-of-the-art methods.

We introduce an approach that creates animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). Existing methods based on neural radiance fields (NeRFs) achieve high-quality novel-view/novel-pose image synthesis but often require days of training and are extremely slow at inference time. Recently the community has explored fast grid structures for efficient training of clothed avatars. Albeit being extremely fast at training these methods can barely achieve an interactive rendering frame rate with around 15 FPS. In this paper we use 3D Gaussian Splatting and learn a non-rigid deformation network to reconstruct animatable clothed human avatars that can be trained within 30 minutes and rendered at real-time frame rates (50+ FPS). Given the explicit nature of our representation we further introduce as-isometric-as-possible regularizations on both the Gaussian mean vectors and the covariance matrices enhancing the generalization of our model on highly articulated unseen poses. Experimental results show that our method achieves comparable and even better performance compared to state-of-the-art approaches on animatable avatar creation from a monocular input while being 400x and 250x faster in training and inference respectively.

This paper introduces 3DFIRES a novel system for scene-level 3D reconstruction from posed images. Designed to work with as few as one view 3DFIRES reconstructs the complete geometry of unseen scenes including hidden surfaces. With multiple view inputs our method produces full reconstruction within all camera frustums. A key feature of our approach is the fusion of multi-view information at the feature level enabling the production of coherent and comprehensive 3D reconstruction. We train our system on non-watertight scans from large-scale real scene dataset. We show it matches the efficacy of single-view reconstruction methods with only one input and surpasses existing techniques in both quantitative and qualitative measures for sparse-view 3D reconstruction.

Text-driven 3D scene generation techniques have made rapid progress in recent years. Their success is mainly attributed to using existing generative models to iteratively perform image warping and inpainting to generate 3D scenes. However these methods heavily rely on the outputs of existing models leading to error accumulation in geometry and appearance that prevent the models from being used in various scenarios (e.g. outdoor and unreal scenarios). To address this limitation we generatively refine the newly generated local views by querying and aggregating global 3D information and then progressively generate the 3D scene. Specifically we employ a tri-plane features-based NeRF as a unified representation of the 3D scene to constrain global 3D consistency and propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior from 2D diffusion model as well as the global 3D information of the current scene. Our extensive experiments demonstrate that in comparison to previous methods our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency.

The lifting of a 3D structure and camera from 2D landmarks is at the cornerstone of the discipline of computer vision. Traditional methods have been confined to specific rigid objects such as those in Perspective-n-Point (PnP) problems but deep learning has expanded our capability to reconstruct a wide range of object classes (e.g. C3DPO [??] and PAUL [??]) with resilience to noise occlusions and perspective distortions. However all these techniques have been limited by the fundamental need to establish correspondences across the 3D training data significantly limiting their utility to applications where one has an abundance of "in-correspondence" 3D data. Our approach harnesses the inherent permutation equivariance of transformers to manage varying numbers of points per 3D data instance withstands occlusions and generalizes to unseen categories. We demonstrate state-of-the-art performance across 2D-3D lifting task benchmarks. Since our approach can be trained across such a broad class of structures we refer to it simply as a 3D Lifting Foundation Model (3D-LFM) -- the first of its kind.

3D facial editing a longstanding task in computer vision with broad applications is expected to fast and intuitively manipulate any face from arbitrary viewpoints following the user's will. Existing works have limitations in terms of intuitiveness generalization and efficiency. To overcome these challenges we propose FaceEdit3D which allows users to directly manipulate 3D points to edit a 3D face achieving natural and rapid face editing. After one or several points are manipulated by users we propose the tri-plane warping to directly manipulate the view-independent 3D representation. To address the problem of distortion caused by tri-plane warping we train a warp-aware encoder to project the warped face onto a standardized latent space. In this space we further propose directional latent editing to mitigate the identity bias caused by the encoder and realize the disentangled editing of various attributes. Extensive experiments show that our method achieves superior results with rich facial details and nice identity preservation. Our approach also supports general applications like multi-attribute continuous editing and cat/car editing. The project website is https://cyh-sj.github.io/FaceEdit3D/.