CVPR 2024 Papers

The remarkable success of Vision Transformers in Artificial Neural Networks (ANNs) has led to a growing interest in incorporating the self-attention mechanism and transformer-based architecture into Spiking Neural Networks (SNNs). While existing methods propose spiking self-attention mechanisms that are compatible with SNNs they lack reasonable scaling methods and the overall architectures proposed by these methods suffer from a bottleneck in effectively extracting local features. To address these challenges we propose a novel spiking self-attention mechanism named Dual Spike Self-Attention (DSSA) with a reasonable scaling method. Based on DSSA we propose a novel spiking Vision Transformer architecture called SpikingResformer which combines the ResNet-based multi-stage architecture with our proposed DSSA to improve both performance and energy efficiency while reducing parameters. Experimental results show that SpikingResformer achieves higher accuracy with fewer parameters and lower energy consumption than other spiking Vision Transformer counterparts. Notably our SpikingResformer-L achieves 79.40% top-1 accuracy on ImageNet with 4 time-steps which is the state-of-the-art result in the SNN field.

Spike cameras leveraging spike-based integration sampling and high temporal resolution offer distinct advantages over standard cameras. However existing approaches reliant on spike cameras often assume optimal illumination a condition frequently unmet in real-world scenarios. To address this we introduce SpikeNeRF the first work that derives a NeRF-based volumetric scene representation from spike camera data. Our approach leverages NeRF's multi-view consistency to establish robust self-supervision effectively eliminating erroneous measurements and uncovering coherent structures within exceedingly noisy input amidst diverse real-world illumination scenarios. The framework comprises two core elements: a spike generation model incorporating an integrate-and-fire neuron layer and parameters accounting for non-idealities such as threshold variation and a spike rendering loss capable of generalizing across varying illumination conditions. We describe how to effectively optimize neural radiance fields to render photorealistic novel views from the novel continuous spike stream demonstrating advantages over other vision sensors in certain scenes. Empirical evaluations conducted on both real and novel realistically simulated sequences affirm the efficacy of our methodology. The dataset and source code are released at https://github.com/BIT-Vision/SpikeNeRF.

Coarse-to-fine 3D instance segmentation methods show weak performances compared to recent Grouping-based Kernel-based and Transformer-based methods. We argue that this is due to two limitations: 1) Instance size overestimation by axis-aligned bounding box(AABB) 2) False negative error accumulation from inaccurate box to the refinement phase. In this work we introduce Spherical Mask a novel coarse-to-fine approach based on spherical representation overcoming those two limitations with several benefits. Specifically our coarse detection estimates each instance with a 3D polygon using a center and radial distance predictions which avoids excessive size estimation of AABB. To cut the error propagation in the existing coarse-to-fine approaches we virtually migrate points based on the polygon allowing all foreground points including false negatives to be refined. During inference the proposal and point migration modules run in parallel and are assembled to form binary masks of instances. We also introduce two margin-based losses for the point migration to enforce corrections for the false positives/negatives and cohesion of foreground points significantly improving the performance. Experimental results from three datasets such as ScanNetV2 S3DIS and STPLS3D show that our proposed method outperforms existing works demonstrating the effectiveness of the new instance representation with spherical coordinates. The code is available at: https://github.com/yunshin/SphericalMask

Vision-based perception for autonomous driving requires an explicit modeling of a 3D space where 2D latent representations are mapped and subsequent 3D operators are applied. However operating on dense latent spaces introduces a cubic time and space complexity which limits scalability in terms of perception range or spatial resolution. Existing approaches compress the dense representation using projections like Bird's Eye View (BEV) or Tri-Perspective View (TPV). Although efficient these projections result in information loss especially for tasks like semantic occupancy prediction. To address this we propose SparseOcc an efficient occupancy network inspired by sparse point cloud processing. It utilizes a lossless sparse latent representation with three key innovations. Firstly a 3D sparse diffuser performs latent completion using spatially decomposed 3D sparse convolutional kernels. Secondly a feature pyramid and sparse interpolation enhance scales with information from others. Finally the transformer head is redesigned as a sparse variant. SparseOcc achieves a remarkable 74.9% reduction on FLOPs over the dense baseline. Interestingly it also improves accuracy from 12.8% to 14.1% mIOU which in part can be attributed to the sparse representation's ability to avoid hallucinations on empty voxels.

Neural approaches have shown a significant progress on camera-based reconstruction. But they require either a fairly dense sampling of the viewing sphere or pre-training on an existing dataset thereby limiting their generalizability. In contrast photometric stereo (PS) approaches have shown great potential for achieving high-quality reconstruction under sparse viewpoints. Yet they are impractical because they typically require tedious laboratory conditions are restricted to dark rooms and often multi-staged making them subject to accumulated errors. To address these shortcomings we propose an end-to-end uncalibrated multi-view PS framework for reconstructing high-resolution shapes acquired from sparse viewpoints in a real-world environment. We relax the dark room assumption and allow a combination of static ambient lighting and dynamic near LED lighting thereby enabling easy data capture outside the lab. Experimental validation confirms that it outperforms existing baseline approaches in the regime of sparse viewpoints by a large margin. This allows to bring high accuracy 3D reconstruction from the dark room to the real world while maintaining a reasonable data capture complexity.

Novel view synthesis of dynamic scenes has been an intriguing yet challenging problem. Despite recent advancements simultaneously achieving high-resolution photorealistic results real-time rendering and compact storage remains a formidable task. To address these challenges we propose Spacetime Gaussian Feature Splatting as a novel dynamic scene representation composed of three pivotal components. First we formulate expressive Spacetime Gaussians by enhancing 3D Gaussians with temporal opacity and parametric motion/rotation. This enables Spacetime Gaussians to capture static dynamic as well as transient content within a scene. Second we introduce splatted feature rendering which replaces spherical harmonics with neural features. These features facilitate the modeling of view- and time-dependent appearance while maintaining small size. Third we leverage the guidance of training error and coarse depth to sample new Gaussians in areas that are challenging to converge with existing pipelines. Experiments on several established real-world datasets demonstrate that our method achieves state-of-the-art rendering quality and speed while retaining compact storage. At 8K resolution our lite-version model can render at 60 FPS on an Nvidia RTX 4090 GPU.

Solving image and video jigsaw puzzles poses the challenging task of rearranging image fragments or video frames from unordered sequences to restore meaningful images and video sequences. Existing approaches often hinge on discriminative models tasked with predicting either the absolute positions of puzzle elements or the permutation actions applied to the original data. Unfortunately these methods face limitations in effectively solving puzzles with a large number of elements. In this paper we propose JPDVT an innovative approach that harnesses diffusion transformers to address this challenge. Specifically we generate positional information for image patches or video frames conditioned on their underlying visual content. This information is then employed to accurately assemble the puzzle pieces in their correct positions even in scenarios involving missing pieces. Our method achieves state-of-the-art performance on several datasets.

Recently there has been a lot of progress in reducing the computation of deep models at inference time. These methods can reduce both the computational needs and power usage of deep models. Some of these approaches adaptively scale the compute based on the input instance. We show that such models can be vulnerable to a universal adversarial patch attack where the attacker optimizes for a patch that when pasted on any image can increase the compute and power consumption of the model. We run experiments with three different efficient vision transformer methods showing that in some cases the attacker can increase the computation to the maximum possible level by simply pasting a patch that occupies only 8% of the image area. We also show that a standard adversarial training defense method can reduce some of the attack's success. We believe adaptive efficient methods will be necessary for the future to lower the power usage of expensive deep models so we hope our paper encourages the community to study the robustness of these methods and develop better defense methods for the proposed attack. Code is available at: https://github.com/UCDvision/SlowFormer.

We introduce multi-slice reasoning a new notion for single-view 3D reconstruction which challenges the current and prevailing belief that multi-view synthesis is the most natural conduit between single-view and 3D. Our key observation is that object slicing is a more direct and hence more advantageous means to reveal occluded structures than altering camera views. Specifically slicing can peel through any occluder without obstruction and in the limit (i.e. with infinitely many slices) it is guaranteed to unveil all hidden object parts. We realize our idea by developing Slice3D a novel method for single-view 3D reconstruction which first predicts multi-slice images from a single RGB input image and then integrates the slices into a 3D model using a coordinate-based transformer network to product a signed distance function. The slice images can be regressed or generated both through a U-Net based network. For the former we inject a learnable slice indicator code to designate each decoded image into a spatial slice location while the slice generator is a denoising diffusion model operating on the entirety of slice images stacked on the input channels. We conduct extensive evaluation against state-of-the-art alternatives to demonstrate superiority of our method especially in recovering complex and severely occluded shape structures amid ambiguities. All Slice3D results were produced by networks trained on a single Nvidia A40 GPU with an inference time of less than 20 seconds.

In this work we explore a novel task of generating human grasps based on single-view scene point clouds which more accurately mirrors the typical real-world situation of observing objects from a single viewpoint. Due to the incompleteness of object point clouds and the presence of numerous scene points the generated hand is prone to penetrating into the invisible parts of the object and the model is easily affected by scene points. Thus we introduce S2HGrasp a framework composed of two key modules: the Global Perception module that globally perceives partial object point clouds and the DiffuGrasp module designed to generate high-quality human grasps based on complex inputs that include scene points. Additionally we introduce S2HGD dataset which comprises approximately 99000 single-object single-view scene point clouds of 1668 unique objects each annotated with one human grasp. Our extensive experiments demonstrate that S2HGrasp can not only generate natural human grasps regardless of scene points but also effectively prevent penetration between the hand and invisible parts of the object. Moreover our model showcases strong generalization capability when applied to unseen objects. Our code and dataset are available at https://github.com/iSEE-Laboratory/S2HGrasp.

Refractive Index Tomography is the inverse problem of reconstructing the continuously-varying 3D refractive index in a scene using 2D projected image measurements. Although a purely refractive field is not directly visible it bends light rays as they travel through space thus providing a signal for reconstruction. The effects of such fields appear in many scientific computer vision settings ranging from refraction due to transparent cells in microscopy to the lensing of distant galaxies caused by dark matter in astrophysics. Reconstructing these fields is particularly difficult due to the complex nonlinear effects of the refractive field on observed images. Furthermore while standard 3D reconstruction and tomography settings typically have access to observations of the scene from many viewpoints many refractive index tomography problem settings only have access to images observed from a single viewpoint. We introduce a method that leverages prior knowledge of light sources scattered throughout the refractive medium to help disambiguate the single-view refractive index tomography problem. We differentiably trace curved rays through a neural field representation of the refractive field and optimize its parameters to best reproduce the observed image. We demonstrate the efficacy of our approach by reconstructing simulated refractive fields analyze the effects of light source distribution on the recovered field and test our method on a simulated dark matter mapping problem where we successfully recover the 3D refractive field caused by a realistic dark matter distribution.

We introduce a novel sequential modeling approach which enables learning a Large Vision Model (LVM) without making use of any linguistic data. To do this we define a common format "visual sentences" in which we can represent raw images and videos as well as annotated data sources such as semantic segmentations and depth reconstructions without needing any meta-knowledge beyond the pixels. Once this wide variety of visual data (comprising 420 billion tokens) is represented as sequences the model can be trained to minimize a cross-entropy loss for next token prediction. By training across various scales of model architecture and data diversity we provide empirical evidence that our models scale effectively. Many different vision tasks can be solved by designing suitable visual prompts at test time.

The perception of motion behavior in a dynamic environment holds significant importance for autonomous driving systems wherein class-agnostic motion prediction methods directly predict the motion of the entire point cloud. While most existing methods rely on fully-supervised learning the manual labeling of point cloud data is laborious and time-consuming. Therefore several annotation-efficient methods have been proposed to address this challenge. Although effective these methods rely on weak annotations or additional multi-modal data like images and the potential benefits inherent in the point cloud sequence are still underexplored. To this end we explore the feasibility of self-supervised motion prediction with only unlabeled LiDAR point clouds. Initially we employ an optimal transport solver to establish coarse correspondences between current and future point clouds as the coarse pseudo motion labels. Training models directly using such coarse labels leads to noticeable spatial and temporal prediction inconsistencies. To mitigate these issues we introduce three simple spatial and temporal regularization losses which facilitate the self-supervised training process effectively. Experimental results demonstrate the significant superiority of our approach over the state-of-the-art self-supervised methods. Code will be available.

State-of-the-art single-view 360 room layout reconstruction methods formulate the problem as a high-level 1D (per-column) regression task. On the other hand traditional low-level 2D layout segmentation is simpler to learn and can represent occluded regions but it requires complex post-processing for the targeting layout polygon and sacrifices accuracy. We present Seg2Reg to render 1D layout depth regression from the 2D segmentation map in a differentiable and occlusion-aware way marrying the merits of both sides. Specifically our model predicts floor-plan density for the input equirectangular 360 image. Formulating the 2D layout representation as a density field enables us to employ 'flattened' volume rendering to form 1D layout depth regression. In addition we propose a novel 3D warping augmentation on layout to improve generalization. Finally we re-implement recent room layout reconstruction methods into our codebase for benchmarking and explore modern backbones and training techniques to serve as the strong baseline. The code is at https: //PanoLayoutStudio.github.io .

Contrastive learning has emerged as a promising paradigm for 3D open-world understanding i.e. aligning point cloud representation to image and text embedding space individually. In this paper we introduce MixCon3D a simple yet effective method aiming to sculpt holistic 3D representation in contrastive language-image-3D pre-training. In contrast to point cloud only we develop the 3D object-level representation from complementary perspectives e.g. multi-view rendered images with the point cloud. Then MixCon3D performs language-3D contrastive learning comprehensively depicting real-world 3D objects and bolstering text alignment. Additionally we pioneer the first thorough investigation of various training recipes for the 3D contrastive learning paradigm building a solid baseline with improved performance. Extensive experiments conducted on three representative benchmarks reveal that our method significantly improves over the baseline surpassing the previous state-of-the-art performance on the challenging 1156-category Objaverse-LVIS dataset by 5.7%. The versatility of MixCon3D is showcased in applications such as text-to-3D retrieval and point cloud captioning further evidencing its efficacy in diverse scenarios. The code is available at https://github.com/UCSC-VLAA/MixCon3D.

Computer vision techniques play a central role in the perception stack of autonomous vehicles. Such methods are employed to perceive the vehicle surroundings given sensor data. 3D LiDAR sensors are commonly used to collect sparse 3D point clouds from the scene. However compared to human perception such systems struggle to deduce the unseen parts of the scene given those sparse point clouds. In this matter the scene completion task aims at predicting the gaps in the LiDAR measurements to achieve a more complete scene representation. Given the promising results of recent diffusion models as generative models for images we propose extending them to achieve scene completion from a single 3D LiDAR scan. Previous works used diffusion models over range images extracted from LiDAR data directly applying image-based diffusion methods. Distinctly we propose to directly operate on the points reformulating the noising and denoising diffusion process such that it can efficiently work at scene scale. Together with our approach we propose a regularization loss to stabilize the noise predicted during the denoising process. Our experimental evaluation shows that our method can complete the scene given a single LiDAR scan as input producing a scene with more details compared to state-of-the-art scene completion methods. We believe that our proposed diffusion process formulation can support further research in diffusion models applied to scene-scale point cloud data.

Despite the success of recent upsampling approaches generating high-resolution point sets with uniform distribution and meticulous structures is still challenging. Unlike existing methods that only take spatial information of the raw data into account we regard point cloud upsampling as generating dense point clouds from deformable topology. Motivated by this we present SPU-PMD a self-supervised topological mesh deformation network for 3D densification. As a cascaded framework our architecture is formulated by a series of coarse mesh interpolator and mesh deformers. At each stage the mesh interpolator first produces the initial dense point clouds via mesh interpolation which allows the model to perceive the primitive topology better. Meanwhile the deformer infers the morphing by estimating the movements of mesh nodes and reconstructs the descriptive topology structure. By associating mesh deformation with feature expansion this module progressively refines point clouds' surface uniformity and structural details. To demonstrate the effectiveness of the proposed method extensive quantitative and qualitative experiments are conducted on synthetic and real-scanned 3D data. Also we compare it with state-of-the-art techniques to further illustrate the superiority of our network. The project page is: https://github.com/lyz21/SPU-PMD

We introduce SODA a self-supervised diffusion model designed for representation learning. The model incorporates an image encoder which distills a source view into a compact representation that in turn guides the generation of related novel views. We show that by imposing a tight bottleneck between the encoder and a denoising decoder and leveraging novel view synthesis as a self-supervised objective we can turn diffusion models into strong representation learners capable of capturing visual semantics in an unsupervised manner. To the best of our knowledge SODA is the first diffusion model to succeed at ImageNet linear-probe classification and at the same time it accomplishes reconstruction editing and synthesis tasks across a wide range of datasets. Further investigation reveals the disentangled nature of its emergent latent space that serves as an effective interface to control and manipulate the produced images. All in all we aim to shed light on the exciting and promising potential of diffusion models not only for image generation but also for learning rich and robust representations. See our website at soda-diffusion.github.io.

In rapidly-evolving domains such as autonomous driving the use of multiple sensors with different modalities is crucial to ensure high operational precision and stability. To correctly exploit the provided information by each sensor in a single common frame it is essential for these sensors to be accurately calibrated. In this paper we leverage the ability of Neural Radiance Fields (NeRF) to represent different sensors modalities in a common volumetric representation to achieve robust and accurate spatio-temporal sensor calibration. By designing a partitioning approach based on the visible part of the scene for each sensor we formulate the calibration problem using only the overlapping areas. This strategy results in a more robust and accurate calibration that is less prone to failure. We demonstrate that our approach works on outdoor urban scenes by validating it on multiple established driving datasets. Results show that our method is able to get better accuracy and robustness compared to existing methods.