CVPR 2024 Papers

In this paper we address the challenge of matching semantically similar keypoints across image pairs. Existing research indicates that the intermediate output of the UNet within the Stable Diffusion (SD) can serve as robust image feature maps for such a matching task. We demonstrate that by employing a basic prompt tuning technique the inherent potential of Stable Diffusion can be harnessed resulting in a significant enhancement in accuracy over previous approaches. We further introduce a novel conditional prompting module that conditions the prompt on the local details of the input image pairs leading to a further improvement in performance. We designate our approach as SD4Match short for Stable Diffusion for Semantic Matching. Comprehensive evaluations of SD4Match on the PF-Pascal PF-Willow and SPair-71k datasets show that it sets new benchmarks in accuracy across all these datasets. Particularly SD4Match outperforms the previous state-of-the-art by a margin of 12 percentage points on the challenging SPair-71k dataset. Code is available at the project website: https://sd4match.active.vision.

Self-supervised landmark estimation is a challenging task that demands the formation of locally distinct feature representations to identify sparse facial landmarks in the absence of annotated data. To tackle this task existing state-of-the-art (SOTA) methods (1) extract coarse features from backbones that are trained with instance-level self-supervised learning (SSL) paradigms which neglect the dense prediction nature of the task (2) aggregate them into memory-intensive hypercolumn formations and (3) supervise lightweight projector networks to naively establish full local correspondences among all pairs of spatial features. In this paper we introduce SCE-MAE a framework that (1) leverages the MAE [??] a region-level SSL method that naturally better suits the landmark prediction task (2) operates on the vanilla feature map instead of on expensive hypercolumns and (3) employs a Correspondence Approximation and Refinement Block (CARB) that utilizes a simple density peak clustering algorithm and our proposed Locality-Constrained Repellence Loss to directly hone only select local correspondences. We demonstrate through extensive experiments that SCE-MAE is highly effective and robust outperforming existing SOTA methods by large margins of 20%-44% on the landmark matching and 9%-15% on the landmark detection tasks.

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.

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.

LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However the computational costs introduced by the dense feature maps grow quadratically as the perception range increases making these models hard to scale up to long-range detection. Some recent works have attempted to construct fully sparse detectors to solve this issue; nevertheless the resulting models either rely on a complex multi-stage pipeline or exhibit inferior performance. In this work we propose a fully sparse adaptive feature diffusion network (SAFDNet) for LiDAR-based 3D object detection. In SAFDNet an adaptive feature diffusion strategy is designed to address the center feature missing problem. We conducted extensive experiments on Waymo Open nuScenes and Argoverse2 datasets. SAFDNet performed slightly better than the previous SOTA on the first two datasets but much better on the last dataset which features long-range detection verifying the efficacy of SAFDNet in scenarios where long-range detection is required. Notably on Argoverse2 SAFDNet surpassed the previous best hybrid detector HEDNet by 2.6% mAP while being 2.1x faster and yielded 2.1% mAP gains over the previous best sparse detector FSDv2 while being 1.3x faster. The code will be available at https://github.com/zhanggang001/HEDNet.

Current 3D stylization methods often assume static scenes which violates the dynamic nature of our real world. To address this limitation we present S-DyRF a reference-based spatio-temporal stylization method for dynamic neural radiance fields. However stylizing dynamic 3D scenes is inherently challenging due to the limited availability of stylized reference images along the temporal axis. Our key insight lies in introducing additional temporal cues besides the provided reference. To this end we generate temporal pseudo-references from the given stylized reference. These pseudo-references facilitate the propagation of style information from the reference to the entire dynamic 3D scene. For coarse style transfer we enforce novel views and times to mimic the style details present in pseudo-references at the feature level. To preserve high-frequency details we create a collection of stylized temporal pseudo-rays from temporal pseudo-references. These pseudo-rays serve as detailed and explicit stylization guidance for achieving fine style transfer. Experiments on both synthetic and real-world datasets demonstrate that our method yields plausible stylized results of space-time view synthesis on dynamic 3D scenes.

Deep neural networks for learning Symmetric Positive Definite (SPD) matrices are gaining increasing attention in machine learning. Despite the significant progress most existing SPD networks use traditional Euclidean classifiers on an approximated space rather than intrinsic classifiers that accurately capture the geometry of SPD manifolds. Inspired by Hyperbolic Neural Networks (HNNs) we propose Riemannian Multinomial Logistics Regression (RMLR) for the classification layers in SPD networks. We introduce a unified framework for building Riemannian classifiers under the metrics pulled back from the Euclidean space and showcase our framework under the parameterized Log-Euclidean Metric (LEM) and Log-Cholesky Metric (LCM). Besides our framework offers a novel intrinsic explanation for the most popular LogEig classifier in existing SPD networks. The effectiveness of our method is demonstrated in three applications: radar recognition human action recognition and electroencephalography (EEG) classification. The code is available at https://github.com/GitZH-Chen/SPDMLR.git.

Many problems in computer vision can be formulated as geometric estimation problems i.e. given a collection of measurements (e.g. point correspondences) we wish to fit a model (e.g. an essential matrix) that agrees with our observations. This necessitates some measure of how much an observation "agrees" with a given model. A natural choice is to consider the smallest perturbation that makes the observation exactly satisfy the constraints. However for many problems this metric is expensive or otherwise intractable to compute. The so-called Sampson error approximates this geometric error through a linearization scheme. For epipolar geometry the Sampson error is a popular choice and in practice known to yield very tight approximations of the corresponding geometric residual (the reprojection error). In this paper we revisit the Sampson approximation and provide new theoretical insights as to why and when this approximation works as well as provide explicit bounds on the tightness under some mild assumptions. Our theoretical results are validated in several experiments on real data and in the context of different geometric estimation tasks.

Despite the growing demand for accurate surface normal estimation models existing methods use general-purpose dense prediction models adopting the same inductive biases as other tasks. In this paper we discuss the inductive biases needed for surface normal estimation and propose to (1) utilize the per-pixel ray direction and (2) encode the relationship between neighboring surface normals by learning their relative rotation. The proposed method can generate crisp - yet piecewise smooth - predictions for challenging in-the-wild images of arbitrary resolution and aspect ratio. Compared to a recent ViT-based state-of-the-art model our method shows a stronger generalization ability despite being trained on an orders of magnitude smaller dataset. The code is available at https://github.com/baegwangbin/DSINE.

Oriented object detection has been developed rapidly in the past few years where rotation equivariance is crucial for detectors to predict rotated boxes. It is expected that the prediction can maintain the corresponding rotation when objects rotate but severe mutation in angular prediction is sometimes observed when objects rotate near the boundary angle which is well-known boundary discontinuity problem. The problem has been long believed to be caused by the sharp loss increase at the angular boundary and widely used joint-optim IoU-like methods deal with this problem by loss-smoothing. However we experimentally find that even state-of-the-art IoU-like methods actually fail to solve the problem. On further analysis we find that the key to solution lies in encoding mode of the smoothing function rather than in joint or independent optimization. In existing IoU-like methods the model essentially attempts to fit the angular relationship between box and object where the break point at angular boundary makes the predictions highly unstable. To deal with this issue we propose a dual-optimization paradigm for angles. We decouple reversibility and joint-optim from single smoothing function into two distinct entities which for the first time achieves the objectives of both correcting angular boundary and blending angle with other parameters. Extensive experiments on multiple datasets show that boundary discontinuity problem is well-addressed. Moreover typical IoU-like methods are improved to the same level without obvious performance gap. The code is available at https://github.com/hangxu-cv/cvpr24acm.

Continual learning methods are known to suffer from catastrophic forgetting a phenomenon that is particularly hard to counter for methods that do not store exemplars of previous tasks. Therefore to reduce potential drift in the feature extractor existing exemplar-free methods are typically evaluated in settings where the first task is significantly larger than subsequent tasks. Their performance drops drastically in more challenging settings starting with a smaller first task. To address this problem of feature drift estimation for exemplar-free methods we propose to adversarially perturb the current samples such that their embeddings are close to the old class prototypes in the old model embedding space. We then estimate the drift in the embedding space from the old to the new model using the perturbed images and compensate the prototypes accordingly. We exploit the fact that adversarial samples are transferable from the old to the new feature space in a continual learning setting. The generation of these images is simple and computationally cheap. We demonstrate in our experiments that the proposed approach better tracks the movement of prototypes in embedding space and outperforms existing methods on several standard continual learning benchmarks as well as on fine-grained datasets. Code is available at https://github.com/dipamgoswami/ADC.

With the recent advances in vision transformers and large language models (LLMs) finetuning costly large models on downstream learning tasks poses significant challenges under limited computational resources. This paper presents a REsource and ComputAtion-efficient Pruning framework (RECAP) for the finetuning of transformer-based large models. RECAP by design bridges the gap between efficiency and performance through an iterative process cycling between pruning finetuning and updating stages to explore different chunks of the given large-scale model. At each iteration we first prune the model with Taylor-approximation-based importance estimation and then only update a subset of the pruned model weights based on the Fisher-information criterion. In this way RECAP achieves two synergistic and yet conflicting goals: reducing the GPU memory footprint while maintaining model performance unlike most existing pruning methods that require the model to be finetuned beforehand for better preservation of model performance. We perform extensive experiments with a wide range of large transformer-based architectures on various computer vision and natural language understanding tasks. Compared to recent pruning techniques we demonstrate that RECAP offers significant improvements in GPU memory efficiency capable of reducing the footprint by up to 65%.

Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding so it is not surprising that the rise of deep learning has led to a breakthrough. The impressive progress of monocular depth estimators has mirrored the growth in model capacity from relatively modest CNNs to large Transformer architectures. Still monocular depth estimators tend to struggle when presented with images with unfamiliar content and layout since their knowledge of the visual world is restricted by the data seen during training and challenged by zero-shot generalization to new domains. This motivates us to explore whether the extensive priors captured in recent generative diffusion models can enable better more generalizable depth estimation. We introduce Marigold a method for affine-invariant monocular depth estimation that is derived from Stable Diffusion and retains its rich prior knowledge. The estimator can be fine-tuned in a couple of days on a single GPU using only synthetic training data. It delivers state-of-the-art performance across a wide range of datasets including over 20% performance gains in specific cases. Project page: https://marigoldmonodepth.github.io.

We propose a novel contrastive learning framework to effectively address the challenges of data heterogeneity in federated learning. We first analyze the inconsistency of gradient updates across clients during local training and establish its dependence on the distribution of feature representations leading to the derivation of the supervised contrastive learning (SCL) objective to mitigate local deviations. In addition we show that a naive integration of SCL into federated learning incurs representation collapse resulting in slow convergence and limited performance gains. To address this issue we introduce a relaxed contrastive learning loss that imposes a divergence penalty on excessively similar sample pairs within each class. This strategy prevents collapsed representations and enhances feature transferability facilitating collaborative training and leading to significant performance improvements. Our framework outperforms all existing federated learning approaches by significant margins on the standard benchmarks as demonstrated by extensive experimental results. The source code is available at our project page(https://github.com/skynbe/FedRCL).

Crowd counting has achieved significant progress by training regressors to predict instance positions. In heavily crowded scenarios however regressors are challenged by uncontrollable annotation variance which causes density map bias and context information inaccuracy. In this study we propose mutual prompt learning (mPrompt) which leverages a regressor and a segmenter as guidance for each other solving bias and inaccuracy caused by annotation variance while distinguishing foreground from background. In specific mPrompt leverages point annotations to tune the segmenter and predict pseudo head masks in a way of point prompt learning. It then uses the predicted segmentation masks which serve as spatial constraint to rectify biased point annotations as context prompt learning. mPrompt defines a way of mutual information maximization from prompt learning mitigating the impact of annotation variance while improving model accuracy. Experiments show that mPrompt significantly reduces the Mean Average Error (MAE) demonstrating the potential to be general framework for down-stream vision tasks. Code is available at https://github.com/csguomy/mPrompt.

Although deep learning based object detection is of great significance for various applications it faces challenges when deployed on edge devices due to the computation and energy limitations. Post-training quantization (PTQ) can improve inference efficiency through integer computing. However they suffer from severe performance degradation when performing full quantization due to overlooking the unique characteristics of regression tasks in object detection. In this paper we are the first to explore regression-friendly quantization and conduct full quantization on various detectors. We reveal the intrinsic reason behind the difficulty of quantizing regressors with empirical and theoretical justifications and introduce a novel Regression-specialized Post-Training Quantization (Reg-PTQ) scheme. It includes Filtered Global Loss Integration Calibration to combine the global loss with a two-step filtering mechanism mitigating the adverse impact of false positive bounding boxes and Learnable Logarithmic-Affine Quantizer tailored for the non-uniform distributed parameters in regression structures. Extensive experiments on prevalent detectors showcase the effectiveness of the well-designed Reg-PTQ. Notably our Reg-PTQ achieves 7.6 times and 5.4 times reduction in computation and storage consumption under INT4 with little performance degradation which indicates the immense potential of fully quantized detectors in real-world object detection applications.

Image stitching from different captures often results in non-rectangular boundaries which is often considered unappealing. To solve non-rectangular boundaries current solutions involve cropping which discards image content inpainting which can introduce unrelated content or warping which can distort non-linear features and introduce artifacts. To overcome these issues we introduce a novel diffusion-based learning framework RecDiffusion for image stitching rectangling. This framework combines Motion Diffusion Models (MDM) to generate motion fields effectively transitioning from the stitched image's irregular borders to a geometrically corrected intermediary. Followed by Content Diffusion Models (CDM) for image detail refinement. Notably our sampling process utilizes a weighted map to identify regions needing correction during each iteration of CDM. Our RecDiffusion ensures geometric accuracy and overall visual appeal surpassing all previous methods in both quantitative and qualitative measures when evaluated on public benchmarks. Code is released at https://github.com/lhaippp/RecDiffusion.

Three-dimensional object detection is one of the key tasks in autonomous driving. To reduce costs in practice low-cost multi-view cameras for 3D object detection are proposed to replace the expansive LiDAR sensors. However relying solely on cameras is difficult to achieve highly accurate and robust 3D object detection. An effective solution to this issue is combining multi-view cameras with the economical millimeter-wave radar sensor to achieve more reliable multi-modal 3D object detection. In this paper we introduce RCBEVDet a radar-camera fusion 3D object detection method in the bird's eye view (BEV). Specifically we first design RadarBEVNet for radar BEV feature extraction. RadarBEVNet consists of a dual-stream radar backbone and a Radar Cross-Section (RCS) aware BEV encoder. In the dual-stream radar backbone a point-based encoder and a transformer-based encoder are proposed to extract radar features with an injection and extraction module to facilitate communication between the two encoders. The RCS-aware BEV encoder takes RCS as the object size prior to scattering the point feature in BEV. Besides we present the Cross-Attention Multi-layer Fusion module to automatically align the multi-modal BEV feature from radar and camera with the deformable attention mechanism and then fuse the feature with channel and spatial fusion layers. Experimental results show that RCBEVDet achieves new state-of-the-art radar-camera fusion results on nuScenes and view-of-delft (VoD) 3D object detection benchmarks. Furthermore RCBEVDet achieves better 3D detection results than all real-time camera-only and radar-camera 3D object detectors with a faster inference speed at 21 28 FPS. The source code will be released at https://github.com/VDIGPKU/RCBEVDet.