CVPR 2024 论文列表

Advances in image diffusion models have recently led to notable improvements in the generation of high-quality images. In combination with Neural Radiance Fields (NeRFs) they enabled new opportunities in 3D generation. However most generative 3D approaches are object-centric and applying them to editing existing photorealistic scenes is not trivial. We propose SIGNeRF a novel approach for fast and controllable NeRF scene editing and scene-integrated object generation. A new generative update strategy ensures 3D consistency across the edited images without requiring iterative optimization. We find that depth-conditioned diffusion models inherently possess the capability to generate 3D consistent views by requesting a grid of images instead of single views. Based on these insights we introduce a multi-view reference sheet of modified images. Our method updates an image collection consistently based on the reference sheet and refines the original NeRF with the newly generated image set in one go. By exploiting the depth conditioning mechanism of the image diffusion model we gain fine control over the spatial location of the edit and enforce shape guidance by a selected region or an external mesh.

Recently efficient Vision Transformers have shown great performance with low latency on resource-constrained devices. Conventionally they use 4x4 patch embeddings and a 4-stage structure at the macro level while utilizing sophisticated attention with multi-head configuration at the micro level. This paper aims to address computational redundancy at all design levels in a memory-efficient manner. We discover that using larger-stride patchify stem not only reduces memory access costs but also achieves competitive performance by leveraging token representations with reduced spatial redundancy from the early stages. Furthermore our preliminary analyses suggest that attention layers in the early stages can be substituted with convolutions and several attention heads in the latter stages are computationally redundant. To handle this we introduce a single-head attention module that inherently prevents head redundancy and simultaneously boosts accuracy by parallelly combining global and local information. Building upon our solutions we introduce SHViT a Single-Head Vision Transformer that obtains the state-of-the-art speed-accuracy tradeoff. For example on ImageNet-1k our SHViT-S4 is 3.3x 8.1x and 2.4x faster than MobileViTv2x1.0 on GPU CPU and iPhone12 mobile device respectively while being 1.3% more accurate. For object detection and instance segmentation on MS COCO using Mask-RCNN head our model achieves performance comparable to FastViT-SA12 while exhibiting 3.8x and 2.0x lower backbone latency on GPU and mobile device respectively.

Scene graphs have been recently introduced into 3D spatial understanding as a comprehensive representation of the scene. The alignment between 3D scene graphs is the first step of many downstream tasks such as scene graph aided point cloud registration mosaicking overlap checking and robot navigation. In this work we treat 3D scene graph alignment as a partial graph-matching problem and propose to solve it with a graph neural network. We reuse the geometric features learned by a point cloud registration method and associate the clustered point-level geometric features with the node-level semantic feature via our designed feature fusion module. Partial matching is enabled by using a learnable method to select the top-k similar node pairs. Subsequent downstream tasks such as point cloud registration are achieved by running a pre-trained registration network within the matched regions. We further propose a point-matching rescoring method that uses the node-wise alignment of the 3D scene graph to reweight the matching candidates from a pre-trained point cloud registration method. It reduces the false point correspondences estimated especially in low-overlapping cases. Experiments show that our method improves the alignment accuracy by 10 20% in low-overlap and random transformation scenarios and outperforms the existing work in multiple downstream tasks. Our code and models are available here (https://github.com/dfki-av/sg-pgm.git).

In this paper we explore the potential of Snapshot Com- pressive Imaging (SCI) technique for recovering the under- lying 3D scene representation from a single temporal com- pressed image. SCI is a cost-effective method that enables the recording of high-dimensional data such as hyperspec- tral or temporal information into a single image using low- cost 2D imaging sensors. To achieve this a series of spe- cially designed 2D masks are usually employed which not only reduces storage requirements but also offers potential privacy protection. Inspired by this to take one step further our approach builds upon the powerful 3D scene represen- tation capabilities of neural radiance fields (NeRF). Specif- ically we formulate the physical imaging process of SCI as part of the training of NeRF allowing us to exploit its impressive performance in capturing complex scene struc- tures. To assess the effectiveness of our method we con- duct extensive evaluations using both synthetic data and real data captured by our SCI system. Extensive experi- mental results demonstrate that our proposed approach sur- passes the state-of-the-art methods in terms of image re- construction and novel view image synthesis. Moreover our method also exhibits the ability to restore high frame- rate multi-view consistent images by leveraging SCI and the rendering capabilities of NeRF. The code is available at https://github.com/WU-CVGL/SCINeRF.

Novel view synthesis for dynamic scenes is still a challenging problem in computer vision and graphics. Recently Gaussian splatting has emerged as a robust technique to represent static scenes and enable high-quality and real-time novel view synthesis. Building upon this technique we propose a new representation that explicitly decomposes the motion and appearance of dynamic scenes into sparse control points and dense Gaussians respectively. Our key idea is to use sparse control points significantly fewer in number than the Gaussians to learn compact 6 DoF transformation bases which can be locally interpolated through learned interpolation weights to yield the motion field of 3D Gaussians. We employ a deformation MLP to predict time-varying 6 DoF transformations for each control point which reduces learning complexities enhances learning abilities and facilitates obtaining temporal and spatial coherent motion patterns. Then we jointly learn the 3D Gaussians the canonical space locations of control points and the deformation MLP to reconstruct the appearance geometry and dynamics of 3D scenes. During learning the location and number of control points are adaptively adjusted to accommodate varying motion complexities in different regions and an ARAP loss following the principle of as rigid as possible is developed to enforce spatial continuity and local rigidity of learned motions. Finally thanks to the explicit sparse motion representation and its decomposition from appearance our method can enable user-controlled motion editing while retaining high-fidelity appearances. Extensive experiments demonstrate that our approach outperforms existing approaches on novel view synthesis with a high rendering speed and enables novel appearance-preserved motion editing applications.

We introduce SAOR a novel approach for estimating the 3D shape texture and viewpoint of an articulated object from a single image captured in the wild. Unlike prior approaches that rely on pre-defined category-specific 3D templates or tailored 3D skeletons SAOR learns to articulate shapes from single-view image collections with a skeleton-free part-based model without requiring any 3D object shape priors. To prevent ill-posed solutions we propose a cross-instance consistency loss that exploits disentangled object shape deformation and articulation. This is helped by a new silhouette-based sampling mechanism to enhance viewpoint diversity during training. Our method only requires estimated object silhouettes and relative depth maps from off-the-shelf pre-trained networks during training. At inference time given a single-view image it efficiently outputs an explicit mesh representation. We obtain improved qualitative and quantitative results on challenging quadruped animals compared to relevant existing work.

Recently the Segment Anything Model (SAM) has showcased remarkable capabilities of zero-shot segmentation while NeRF (Neural Radiance Fields) has gained popularity as a method for various 3D problems beyond novel view synthesis. Though there exist initial attempts to incorporate these two methods into 3D segmentation they face the challenge of accurately and consistently segmenting objects in complex scenarios. In this paper we introduce the Segment Anything for NeRF in High Quality (SANeRF-HQ) to achieve high-quality 3D segmentation of any target object in a given scene. SANeRF-HQ utilizes SAM for open-world object segmentation guided by user-supplied prompts while leveraging NeRF to aggregate information from different viewpoints. To overcome the aforementioned challenges we employ density field and RGB similarity to enhance the accuracy of segmentation boundary during the aggregation. Emphasizing on segmentation accuracy we evaluate our method on multiple NeRF datasets where high-quality ground-truths are available or manually annotated. SANeRF-HQ shows a significant quality improvement over state-of-the-art methods in NeRF object segmentation provides higher flexibility for object localization and enables more consistent object segmentation across multiple views.

This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS) with a focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. The former arises from non-uniform point sampling allowing models to distinguish the density disparities between foreground and background for easier segmentation. The latter results from sampling only 2048 points limiting semantic information and deviating from the real-world practice. To address these issues we introduce a standardized FS-PCS setting upon which a new benchmark is built. Moreover we propose a novel FS-PCS model. While previous methods are based on feature optimization by mainly refining support features to enhance prototypes our method is based on correlation optimization referred to as Correlation Optimization Segmentation (COSeg). Specifically we compute Class-specific Multi-prototypical Correlation (CMC) for each query point representing its correlations to category prototypes. Then we propose the Hyper Correlation Augmentation (HCA) module to enhance CMC. Furthermore tackling the inherent property of few-shot training to incur base susceptibility for models we propose to learn non-parametric prototypes for the base classes during training. The learned base prototypes are used to calibrate correlations for the background class through a Base Prototypes Calibration (BPC) module. Experiments on popular datasets demonstrate the superiority of COSeg over existing methods. The code is available at github.com/ZhaochongAn/COSeg.

In this work we present RepKPU an efficient network for point cloud upsampling. We propose to promote upsampling performance by exploiting better shape representation and point generation strategy. Inspired by KPConv we propose a novel representation called RepKPoints to effectively characterize the local geometry whose advantages over prior representations are as follows: (1) density-sensitive; (2) large receptive fields; (3) position-adaptive which makes RepKPoints a generalized form of previous representations. Moreover we propose a novel paradigm namely Kernel-to-Displacement generation for point generation where point cloud upsampling is reformulated as the deformation of kernel points. Specifically we propose KP-Queries which is a set of kernel points with predefined positions and learned features to serve as the initial state of upsampling. Using cross-attention mechanisms we achieve interactions between RepKPoints and KP-Queries and subsequently KP-Queries are converted to displacement features followed by a MLP to predict the new positions of KP-Queries which serve as the generated points. Extensive experimental results demonstrate that RepKPU outperforms state-of-the-art methods on several widely-used benchmark datasets with high efficiency.

Vision language models (VLMs) have experienced rapid advancements through the integration of large language models (LLMs) with image-text pairs yet they struggle with detailed regional visual understanding due to limited spatial awareness of the vision encoder and the use of coarse-grained training data that lacks detailed region-specific captions. To address this we introduce RegionGPT (short as RGPT) a novel framework designed for complex region-level captioning and understanding. RGPT enhances the spatial awareness of regional representation with simple yet effective modifications to existing visual encoders in VLMs. We further improve performance on tasks requiring a specific output scope by integrating task-guided instruction prompts during both training and inference phases while maintaining the model's versatility for general-purpose tasks. Additionally we develop an automated region caption data generation pipeline enriching the training set with detailed region-level captions. We demonstrate that a universal RGPT model can be effectively applied and significantly enhancing performance across a range of region-level tasks including but not limited to complex region descriptions reasoning object classification and referring expressions comprehension.

Scene-aware Adaptive Compressive Sensing (ACS) has constituted a persistent pursuit holding substantial promise for the enhancement of Compressive Sensing (CS) performance. Cascaded ACS furnishes a proficient multi-stage framework for adaptively allocating the CS sampling based on previous CS measurements. However reconstruction is commonly required for analyzing and steering the successive CS sampling which bottlenecks the ACS speed and impedes the practical application in time-sensitive scenarios. Addressing this challenge we propose a reconstruction-free cascaded ACS method which requires NO reconstruction during the adaptive sampling process. A lightweight Score Network (ScoreNet) is proposed to directly determine the ACS allocation with previous CS measurements and a differentiable adaptive sampling module is proposed for end-to-end training. For image reconstruction we propose a Multi-Grid Spatial-Attention Network (MGSANet) that could facilitate efficient multi-stage training and inferencing. By introducing the reconstruction-fidelity supervision outside the loop of the multi-stage sampling process ACS can be efficiently optimized and achieve high imaging fidelity. The effectiveness of the proposed method is demonstrated with extensive quantitative and qualitative experiments compared with the state-of-the-art CS algorithms.

We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery HaMeR follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR's success lies in scaling up both the data used for training and the capacity of the deep network for hand reconstruction. For training data we combine multiple datasets that contain 2D or 3D hand annotations. For the deep model we use a large scale Vision Transformer architecture. Our final model consistently outperforms the previous baselines on popular 3D hand pose benchmarks. To further evaluate the effect of our design in non-controlled settings we annotate existing in-the-wild datasets with 2D hand keypoint annotations. On this newly collected dataset of annotations HInt we demonstrate significant improvements over existing baselines. We will make our code data and models publicly available upon publication. We make our code data and models available on the project website: https://geopavlakos.github.io/hamer/.

3D reconstruction methods such as Neural Radiance Fields (NeRFs) excel at rendering photorealistic novel views of complex scenes. However recovering a high-quality NeRF typically requires tens to hundreds of input images resulting in a time-consuming capture process. We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis trained on synthetic and multiview datasets which regularizes a NeRF-based 3D reconstruction pipeline at novel camera poses beyond those captured by the set of input images. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions. We perform an extensive evaluation across various real-world datasets including forward-facing and 360-degree scenes demonstrating significant performance improvements over previous few-view NeRF reconstruction approaches. Please see our project page at reconfusion.github.io.

Synthesizing realistic videos of talking faces under custom lighting conditions and viewing angles benefits various downstream applications like video conferencing. However most existing relighting methods are either time-consuming or unable to adjust the viewpoints. In this paper we present the first real-time 3D-aware method for relighting in-the-wild videos of talking faces based on Neural Radiance Fields (NeRF). Given an input portrait video our method can synthesize talking faces under both novel views and novel lighting conditions with a photo-realistic and disentangled 3D representation. Specifically we infer an albedo tri-plane as well as a shading tri-plane based on a desired lighting condition for each video frame with fast dual-encoders. We also leverage a temporal consistency network to ensure smooth transitions and reduce flickering artifacts. Our method runs at 32.98 fps on consumer-level hardware and achieves state-of-the-art results in terms of reconstruction quality lighting error lighting instability temporal consistency and inference speed. We demonstrate the effectiveness and interactivity of our method on various portrait videos with diverse lighting and viewing conditions.

Vision Transformers (ViTs) have emerged as a compelling alternative to Convolutional Neural Networks (CNNs) in the realm of computer vision showcasing tremendous potential. However recent research has unveiled a susceptibility of ViTs to adversarial attacks akin to their CNN counterparts. Adversarial training and randomization are two representative effective defenses for CNNs. Some researchers have attempted to apply adversarial training to ViTs and achieved comparable robustness to CNNs while it is not easy to directly apply randomization to ViTs because of the architecture difference between CNNs and ViTs. In this paper we delve into the structural intricacies of ViTs and propose a novel defense mechanism termed Random entangled image Transformer (ReiT) which seamlessly integrates adversarial training and randomization to bolster the adversarial robustness of ViTs. Recognizing the challenge posed by the structural disparities between ViTs and CNNs we introduce a novel module input-independent random entangled self-attention (II-ReSA). This module optimizes random entangled tokens that lead to "dissimilar" self-attention outputs by leveraging model parameters and the sampled random tokens thereby synthesizing the self-attention module outputs and random entangled tokens to diminish adversarial similarity. ReiT incorporates two distinct random entangled tokens and employs dual randomization offering an effective countermeasure against adversarial examples while ensuring comprehensive deduction guarantees. Through extensive experiments conducted on various ViT variants and benchmarks we substantiate the superiority of our proposed method in enhancing the adversarial robustness of Vision Transformers.

This paper introduces a versatile paradigm for integrating multi-view reflectance (optional) and normal maps acquired through photometric stereo. Our approach employs a pixel-wise joint re-parameterization of reflectance and normal considering them as a vector of radiances rendered under simulated varying illumination. This re-parameterization enables the seamless integration of reflectance and normal maps as input data in neural volume rendering-based 3D reconstruction while preserving a single optimization objective. In contrast recent multi-view photometric stereo (MVPS) methods depend on multiple potentially conflicting objectives. Despite its apparent simplicity our proposed approach outperforms state-of-the-art approaches in MVPS benchmarks across F-score Chamfer distance and mean angular error metrics. Notably it significantly improves the detailed 3D reconstruction of areas with high curvature or low visibility.

Vision Transformer (ViT) has gained increasing attention in the computer vision community in recent years. However the core component of ViT Self-Attention lacks explicit spatial priors and bears a quadratic computational complexity thereby constraining the applicability of ViT. To alleviate these issues we draw inspiration from the recent Retentive Network (RetNet) in the field of NLP and propose RMT a strong vision backbone with explicit spatial prior for general purposes. Specifically we extend the RetNet's temporal decay mechanism to the spatial domain and propose a spatial decay matrix based on the Manhattan distance to introduce the explicit spatial prior to Self-Attention. Additionally an attention decomposition form that adeptly adapts to explicit spatial prior is proposed aiming to reduce the computational burden of modeling global information without disrupting the spatial decay matrix. Based on the spatial decay matrix and the attention decomposition form we can flexibly integrate explicit spatial prior into the vision backbone with linear complexity. Extensive experiments demonstrate that RMT exhibits exceptional performance across various vision tasks. Specifically without extra training data RMT achieves 84.8% and 86.1% top-1 acc on ImageNet-1k with 27M/4.5GFLOPs and 96M/18.2GFLOPs. For downstream tasks RMT achieves 54.5 box AP and 47.2 mask AP on the COCO detection task and 52.8 mIoU on the ADE20K semantic segmentation task.

We introduce a new RGB-D object dataset captured in the wild called WildRGB-D. Unlike most existing real-world object-centric datasets which only come with RGB capturing the direct capture of the depth channel allows better 3D annotations and broader downstream applications. WildRGB-D comprises large-scale category-level RGB-D object videos which are taken using an iPhone to go around the objects in 360 degrees. It contains around 8500 recorded objects and nearly 20000 RGB-D videos across 46 common object categories. These videos are taken with diverse cluttered backgrounds with three setups to cover as many real-world scenarios as possible: (i) a single object in one video; (ii) multiple objects in one video; and (iii) an object with a static hand in one video. The dataset is annotated with object masks real-world scale camera poses and reconstructed aggregated point clouds from RGBD videos. We benchmark four tasks with WildRGB-D including novel view synthesis camera pose estimation object 6d pose estimation and object surface reconstruction. Our experiments show that the large-scale capture of RGB-D objects provides a large potential to advance 3D object learning. Our project page is https://wildrgbd.github.io/.

Comprehensive capturing of human motions requires both accurate captures of complex poses and precise localization of the human within scenes. Most of the HPE datasets and methods primarily rely on RGB LiDAR or IMU data. However solely using these modalities or a combination of them may not be adequate for HPE particularly for complex and fast movements. For holistic human motion understanding we present RELI11D a high-quality multimodal human motion dataset involves LiDAR IMU system RGB camera and Event camera. It records the motions of 10 actors performing 5 sports in 7 scenes including 3.32 hours of synchronized LiDAR point clouds IMU measurement data RGB videos and Event steams. Through extensive experiments we demonstrate that the RELI11D presents considerable challenges and opportunities as it contains many rapid and complex motions that require precise location. To address the challenge of integrating different modalities we propose LEIR a multimodal baseline that effectively utilizes LiDAR Point Cloud Event stream and RGB through our cross-attention fusion strategy. We show that LEIR exhibits promising results for rapid motions and daily motions and that utilizing the characteristics of multiple modalities can indeed improve HPE performance. Both the dataset and source code will be released publicly to the research community fostering collaboration and enabling further exploration in this field.