CVPR 2024 Papers

In this work we propose a novel discriminative framework for dexterous grasp generation named Dexterous Grasp TRansformer (DGTR) capable of predicting a diverse set of feasible grasp poses by processing the object point cloud with only one forward pass. We formulate dexterous grasp generation as a set prediction task and design a transformer-based grasping model for it. However we identify that this set prediction paradigm encounters several optimization challenges in the field of dexterous grasping and results in restricted performance. To address these issues we propose progressive strategies for both the training and testing phases. First the dynamic-static matching training (DSMT) strategy is presented to enhance the optimization stability during the training phase. Second we introduce the adversarial-balanced test-time adaptation (AB-TTA) with a pair of adversarial losses to improve grasping quality during the testing phase. Experimental results on the DexGraspNet dataset demonstrate the capability of DGTR to predict dexterous grasp poses with both high quality and diversity. Notably while keeping high quality the diversity of grasp poses predicted by DGTR significantly outperforms previous works in multiple metrics without any data pre-processing. Codes are available at https://github.com/iSEE-Laboratory/DGTR.

Neural network pruning particularly channel pruning is a widely used technique for compressing deep learning models to enable their deployment on edge devices with limited resources. Typically redundant weights or structures are removed to achieve the target resource budget. Although data-driven pruning approaches have proven to be more effective they cannot be directly applied to federated learning (FL) which has emerged as a popular technique in edge computing applications because of distributed and confidential datasets. In response to this challenge we design a new network pruning method for FL. We propose device-wise sub-networks for each device assuming that the data distribution is similar within each device. These sub-networks are generated through sub-network embeddings and a hypernetwork. To further minimize memory usage and communication costs we permanently prune the full model to remove weights that are not useful for all devices. During the FL process we simultaneously train the device-wise sub-networks and the base sub-network to facilitate the pruning process. We then finetune the pruned model with device-wise sub-networks to regain performance. Moreover we provided the theoretical guarantee of convergence for our method. Our method achieves better performance and resource trade-off than other well-established network pruning baselines as demonstrated through extensive experiments on CIFAR-10 CIFAR-100 and TinyImageNet.

We introduce the video detours problem for navigating instructional videos. Given a source video and a natural language query asking to alter the how-to video's current path of execution in a certain way the goal is to find a related "detour video" that satisfies the requested alteration. To address this challenge we propose VidDetours a novel video-language approach that learns to retrieve the targeted temporal segments from a large repository of how-to's using video-and-text conditioned queries. Furthermore we devise a language-based pipeline that exploits how-to video narration text to create weakly supervised training data. We demonstrate our idea applied to the domain of how-to cooking videos where a user can detour from their current recipe to find steps with alternate ingredients tools and techniques. Validating on a ground truth annotated dataset of 16K samples we show our model's significant improvements over best available methods for video retrieval and question answering with recall rates exceeding the state of the art by 35%.

We propose a structure-from-motion framework to recover accurate camera poses and point clouds from unordered images. Traditional SfM systems typically rely on the successful detection of repeatable keypoints across multiple views as the first step which is difficult for texture-poor scenes and poor keypoint detection may break down the whole SfM system. We propose a detector-free SfM framework to draw benefits from the recent success of detector-free matchers to avoid the early determination of keypoints while solving the multi-view inconsistency issue of detector-free matchers. Specifically our framework first reconstructs a coarse SfM model from quantized detector-free matches. Then it refines the model by a novel iterative refinement pipeline which iterates between an attention-based multi-view matching module to refine feature tracks and a geometry refinement module to improve the reconstruction accuracy. Experiments demonstrate that the proposed framework outperforms existing detector-based SfM systems on common benchmark datasets. We also collect a texture-poor SfM dataset to demonstrate the capability of our framework to reconstruct texture-poor scenes. Based on this framework we take first place in Image Matching Challenge 2023.

Current perceptive models heavily depend on resource-intensive datasets prompting the need for innovative solutions. Leveraging recent advances in diffusion models synthetic data by constructing image inputs from various annotations proves beneficial for downstream tasks. While prior methods have separately addressed generative and perceptive models DetDiffusion for the first time harmonizes both tackling the challenges in generating effective data for perceptive models. To enhance image generation with perceptive models we introduce perception-aware loss (P.A. loss) through segmentation improving both quality and controllability. To boost the performance of specific perceptive models our method customizes data augmentation by extracting and utilizing perception-aware attribute (P.A. Attr) during generation. Experimental results from the object detection task highlight DetDiffusion's superior performance establishing a new state-of-the-art in layout-guided generation. Furthermore image syntheses from DetDiffusion can effectively augment training data significantly enhancing downstream detection performance.

Existing open-vocabulary object detectors typically require a predefined set of categories from users significantly confining their application scenarios. In this paper we introduce DetCLIPv3 a high-performing detector that excels not only at both open-vocabulary object detection but also generating hierarchical labels for detected objects. DetCLIPv3 is characterized by three core designs: 1. Versatile model architecture: we derive a robust open-set detection framework which is further empowered with generation ability via the integration of a caption head. 2. High information density data: we develop an auto-annotation pipeline leveraging visual large language model to refine captions for large-scale image-text pairs providing rich multi-granular object labels to enhance the training. 3. Efficient training strategy: we employ a pre-training stage with low-resolution inputs that enables the object captioner to efficiently learn a broad spectrum of visual concepts from extensive image-text paired data. This is followed by a fine-tuning stage that leverages a small number of high-resolution samples to further enhance detection performance. With these effective designs DetCLIPv3 demonstrates superior open-vocabulary detection performance e.g. our Swin-T backbone model achieves a notable 47.0 zero-shot fixed AP on the LVIS minival benchmark outperforming GLIPv2 GroundingDINO and DetCLIPv2 by 18.0/19.6/6.6 AP respectively. DetCLIPv3 also achieves a state-of-the-art 19.7 AP in dense captioning task on VG dataset showcasing its strong generative capability.

In recent years there has been a significant shift in the field of digital avatar research towards modeling animating and reconstructing clothed human representations as a key step towards creating realistic avatars. However current 3D cloth generation methods are garment specific or trained completely on synthetic data hence lacking fine details and realism. In this work we make a step towards automatic realistic garment design and propose Design2Cloth a high fidelity 3D generative model trained on a real world dataset from more than 2000 subject scans. To provide vital contribution to the fashion industry we developed a user-friendly adversarial model capable of generating diverse and detailed clothes simply by drawing a 2D cloth mask. Under a series of both qualitative and quantitative experiments we showcase that Design2Cloth outperforms current state-of-the-art cloth generative models by a large margin. In addition to the generative properties of our network we showcase that the proposed method can be used to achieve high quality reconstructions from single in-the-wild images and 3D scans. Dataset code and pre-trained model will become publicly available.

Templates serve as a good starting point to implement a design (e.g. banner slide) but it takes great effort from designers to manually create. In this paper we present Desigen an automatic template creation pipeline which generates background images as well as harmonious layout elements over the background. Different from natural images a background image should preserve enough non-salient space for the overlaying layout elements. To equip existing advanced diffusion-based models with stronger spatial control we propose two simple but effective techniques to constrain the saliency distribution and reduce the attention weight in desired regions during the background generation process. Then conditioned on the background we synthesize the layout with a Transformer-based autoregressive generator. To achieve a more harmonious composition we propose an iterative inference strategy to adjust the synthesized background and layout in multiple rounds. We constructed a design dataset with more than 40k advertisement banners to verify our approach. Extensive experiments demonstrate that the proposed pipeline generates high-quality templates comparable to human designers. More than a single-page design we further show an application of presentation generation that outputs a set of theme-consistent slides. The data and code are available at https://whaohan.github.io/desigen.

Over the past year a large body of multimodal research has emerged around zero-shot evaluation using GPT descriptors. These studies boost the zero-shot accuracy of pretrained VL models with an ensemble of label-specific text generated by GPT. A recent study WaffleCLIP demonstrated that similar zero-shot accuracy can be achieved with an ensemble of random descriptors. However both zero-shot methods are un-trainable and consequently sub-optimal when some few-shot out-of-distribution (OOD) training data is available. Inspired by these prior works we present two more flexible methods called descriptor and word soups which do not require an LLM at test time and can leverage training data to increase OOD target accuracy. Descriptor soup greedily selects a small set of textual descriptors using generic few-shot training data then calculates robust class embeddings using the selected descriptors. Word soup greedily assembles a chain of words in a similar manner. Compared to existing few-shot soft prompt tuning methods word soup requires fewer parameters by construction and less GPU memory since it does not require backpropagation. Both soups outperform current published few-shot methods even when combined with SoTA zero-shot methods on cross-dataset and domain generalization benchmarks. Compared with SoTA prompt and descriptor ensembling methods such as ProDA and WaffleCLIP word soup achieves higher OOD accuracy with fewer ensemble members. Please checkout our code: https://github.com/Chris210634/word_soups

How do two sets of images differ? Discerning set-level differences is crucial for understanding model behaviors and analyzing datasets yet manually sifting through thousands of images is impractical. To aid in this discovery process we explore the task of automatically describing the differences between two sets of images which we term Set Difference Captioning. This task takes in image sets \mathcal D _A and \mathcal D _B and outputs a description that is more often true on \mathcal D _A than \mathcal D _B. We outline a two-stage approach that first proposes candidate difference descriptions from image sets and then re-ranks the candidates by checking how well they can differentiate the two sets. We introduce VisDiff which first captions the images and prompts a language model to propose candidate descriptions then re-ranks these descriptions using CLIP. To evaluate VisDiff we collect VisDiffBench a dataset with 187 paired image sets with ground truth difference descriptions. We apply VisDiff to various domains such as comparing datasets (e.g. ImageNet vs. ImageNetV2) comparing classification models (e.g. zero-shot CLIP vs. supervised ResNet) characterizing differences between generative models (e.g. StableDiffusionV1 and V2) and discovering what makes images memorable. Using VisDiff we are able to find interesting and previously unknown differences in datasets and models demonstrating its utility in revealing nuanced insights.

Concealed Object Detection (COD) aims to identify objects visually embedded in their background. Existing COD datasets and methods predominantly focus on animals or humans ignoring the agricultural domain which often contains numerous small and concealed crops with severe occlusions. In this paper we introduce Concealed Crop Detection (CCD) which extends classic COD to agricultural domains. Experimental study shows that unimodal data provides insufficient information for CCD. To address this gap we first collect a large-scale RGB-D dataset ACOD-12K containing high-resolution crop images and depth maps. Then we propose a foundational framework named Recurrent Iterative Segmentation Network (RISNet). To tackle the challenge of dense objects we employ multi-scale receptive fields to capture objects of varying sizes thus enhancing the detection performance for dense objects. By fusing depth features our method can acquire spatial information about concealed objects to mitigate disturbances caused by intricate backgrounds and occlusions. Furthermore our model adopts a multi-stage iterative approach using predictions from each stage as gate attention to reinforce position information thereby improving the detection accuracy for small objects. Extensive experimental results demonstrate that our RISNet achieves new state-of-the-art performance on both newly proposed CCD and classic COD tasks. All resources will be available at https://github.com/Kki2Eve/RISNet.

Dense depth maps have been used as a key element of visual perception tasks. There have been tremendous efforts to enhance the depth quality ranging from optimization-based to learning-based methods. Despite the remarkable progress for a long time their applicability in the real world is limited due to systematic measurement biases such as density sensing pattern and scan range. It is well-known that the biases make it difficult for these methods to achieve their generalization. We observe that learning a joint representation for input modalities (e.g. images and depth) which most recent methods adopt is sensitive to the biases. In this work we disentangle those modalities to mitigate the biases with prompt engineering. For this we design a novel depth prompt module to allow the desirable feature representation according to new depth distributions from either sensor types or scene configurations. Our depth prompt can be embedded into foundation models for monocular depth estimation. Through this embedding process our method helps the pretrained model to be free from restraint of depth scan range and to provide absolute scale depth maps. We demonstrate the effectiveness of our method through extensive evaluations. Source code is publicly available at https://github.com/JinhwiPark/DepthPrompting.

Recovering a clear image from a single hazy image is an open inverse problem. Although significant research progress has been made most existing methods ignore the effect that downstream tasks play in promoting upstream dehazing. From the perspective of the haze generation mechanism there is a potential relationship between the depth information of the scene and the hazy image. Based on this we propose a dual-task collaborative mutual promotion framework to achieve the dehazing of a single image. This framework integrates depth estimation and dehazing by a dual-task interaction mechanism and achieves mutual enhancement of their performance. To realize the joint optimization of the two tasks an alternative implementation mechanism with the difference perception is developed. On the one hand the difference perception between the depth maps of the dehazing result and the ideal image is proposed to promote the dehazing network to pay attention to the non-ideal areas of the dehazing. On the other hand by improving the depth estimation performance in the difficult-to-recover areas of the hazy image the dehazing network can explicitly use the depth information of the hazy image to assist the clear image recovery. To promote the depth estimation we propose to use the difference between the dehazed image and the ground truth to guide the depth estimation network to focus on the dehazed unideal areas. It allows dehazing and depth estimation to leverage their strengths in a mutually reinforcing manner. Experimental results show that the proposed method can achieve better performance than that of the state-of-the-art approaches. The source code is released at https://github.com/zhoushen1/DCMPNet.

This work presents Depth Anything a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules we aim to build a simple yet powerful foundation model dealing with any images under any circumstances. To this end we scale up the dataset by designing a data engine to collect and automatically annotate large-scale unlabeled data ( 62M) which significantly enlarges the data coverage and thus is able to reduce the generalization error. We investigate two simple yet effective strategies that make data scaling-up promising. First a more challenging optimization target is created by leveraging data augmentation tools. It compels the model to actively seek extra visual knowledge and acquire robust representations. Second an auxiliary supervision is developed to enforce the model to inherit rich semantic priors from pre-trained encoders. We evaluate its zero-shot capabilities extensively including six public datasets and randomly captured photos. It demonstrates impressive generalization ability. Further through fine-tuning it with metric depth information from NYUv2 and KITTI new SOTAs are set. Our better depth model also results in a better depth-conditioned ControlNet. Our models are released at https://github.com/LiheYoung/Depth-Anything.

3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task but its performance is limited by different sensor sampling patterns (i.e. variations in point density) and incomplete training strategies. In this work we propose a density-guided translator (DGT) which translates point density between domains and integrates it into a two-stage self-training pipeline named DGT-ST. First in contrast to existing works that simultaneously conduct data generation and feature/output alignment within unstable adversarial training we employ the non-learnable DGT to bridge the domain gap at the input level. Second to provide a well-initialized model for self-training we propose a category-level adversarial network in stage one that utilizes the prototype to prevent negative transfer. Finally by leveraging the designs above a domain-mixed self-training method with source-aware consistency loss is proposed in stage two to narrow the domain gap further. Experiments on two synthetic-to-real segmentation tasks (SynLiDAR ? semanticKITTI and SynLiDAR ? semanticPOSS) demonstrate that DGT-ST outperforms state-of-the-art methods achieving 9.4% and 4.3% mIoU improvements respectively. Code is available at https://github.com/yuan-zm/DGT-ST.

Densely annotating the large-scale point clouds is laborious. To alleviate the annotation burden contrastive learning has attracted increasing attention for tackling semi-supervised 3D semantic segmentation. However existing point-to-point contrastive learning techniques in literature are generally sensitive to outliers resulting in insufficient modeling of the point-wise representations. To address this problem we propose a method named DDSemi for semi-supervised 3D semantic segmentation where a density-guided contrastive learning technique is explored. This technique calculates the contrastive loss in a point-to-anchor manner by estimating an anchor for each class from the memory bank based on the finding that the cluster centers tend to be located in dense regions. In this technique an inter-contrast loss is derived from the perturbed unlabeled point cloud pairs while an intra-contrast loss is derived from a single unlabeled point cloud. The derived losses could enhance the discriminability of the features and implicitly constrain the semantic consistency between the perturbed unlabeled point cloud pairs. In addition we propose a dual-space hardness sampling strategy to pay more attention to the hard samples located in sparse regions of both the geometric space and feature space by reweighting the point-wise intra-contrast loss. Experimental results on both indoor-scene and outdoor-scene datasets demonstrate that the proposed method outperforms the comparative state-of-the-art semi-supervised methods.

Multi-agent trajectory prediction is essential in autonomous driving risk avoidance and traffic flow control. However the heterogeneous traffic density on interactions which caused by physical laws social norms and so on is often overlooked in existing methods. When the density varies the number of agents involved in interactions and the corresponding interaction probability change dynamically. To tackle this issue we propose a new method called \underline D ensity-\underline A daptive Model based on \underline M otif \underline M atrix for Multi-Agent Trajectory Prediction (DAMM) to gain insights into multi-agent systems. Here we leverage the motif matrix to represent dynamic connectivity in a higher-order pattern and distill the interaction information from the perspectives of the spatial and the temporal dimensions. Specifically in spatial dimension we utilize multi-scale feature fusion to adaptively select the optimal range of neighbors participating in interactions for each time slot. In temporal dimension we extract the temporal interaction features and adapt a pyramidal pooling layer to generate the interaction probability for each agent. Experimental results demonstrate that our approach surpasses state-of-the-art methods on autonomous driving dataset.

Few-shot model compression aims to compress a large model into a more compact one with only a tiny training set (even without labels). Block-level pruning has recently emerged as a leading technique in achieving high accuracy and low latency in few-shot CNN compression. But few-shot compression for Vision Transformers (ViT) remains largely unexplored which presents a new challenge. In particular the issue of sparse compression exists in traditional CNN few-shot methods which can only produce very few compressed models of different model sizes. This paper proposes a novel framework for few-shot ViT compression named DC-ViT. Instead of dropping the entire block DC-ViT selectively eliminates the attention module while retaining and reusing portions of the MLP module. DC-ViT enables dense compression which outputs numerous compressed models that densely populate the range of model complexity. DC-ViT outperforms state-of-the-art few-shot compression methods by a significant margin of 10 percentage points along with lower latency in the compression of ViT and its variants.