Four-dimensional Digital Subtraction Angiography (4D DSA) is a medical imaging technique that provides a series of 2D images captured at different stages and angles during the process of contrast agent filling blood vessels. It plays a significant role in the diagnosis of cerebrovascular diseases. Improving the rendering quality and speed under sparse sampling is important for observing the status and location of lesions. The current methods exhibit inadequate rendering quality in sparse views and suffer from slow rendering speed. To overcome these limitations, we propose TOGS, a Gaussian splatting method with opacity offset over time, which can effectively improve the rendering quality and speed of 4D DSA. We introduce an opacity offset table for each Gaussian to model the temporal variations in the radiance of the contrast agent. By interpolating the opacity offset table, the opacity variation of the Gaussian at different time points can be determined. This enables us to render the 2D DSA image at that specific moment. Additionally, we introduced a Smooth loss term in the loss function to mitigate overfitting issues that may arise in the model when dealing with sparse view scenarios. During the training phase, we randomly prune Gaussians, thereby reducing the storage overhead of the model. The experimental results demonstrate that compared to previous methods, this model achieves state-of-the-art reconstruction quality under the same number of training views. Additionally, it enables real-time rendering while maintaining low storage overhead. The code will be publicly available.
Gaze following aims to interpret human-scene interactions by predicting the person's focal point of gaze. Prevailing approaches often use multi-modality inputs, most of which adopt a two-stage framework. Hence their performance highly depends on the previous prediction accuracy. Others use a single-modality approach with complex decoders, increasing network computational load. Inspired by the remarkable success of pre-trained plain Vision Transformers (ViTs), we introduce a novel single-modality gaze following framework, ViTGaze. In contrast to previous methods, ViTGaze creates a brand new gaze following framework based mainly on powerful encoders (dec. param. less than 1%). Our principal insight lies in that the inter-token interactions within self-attention can be transferred to interactions between humans and scenes. Leveraging this presumption, we formulate a framework consisting of a 4D interaction encoder and a 2D spatial guidance module to extract human-scene interaction information from self-attention maps. Furthermore, our investigation reveals that ViT with self-supervised pre-training exhibits an enhanced ability to extract correlated information. A large number of experiments have been conducted to demonstrate the performance of the proposed method. Our method achieves state-of-the-art (SOTA) performance among all single-modality methods (3.4% improvement on AUC, 5.1% improvement on AP) and very comparable performance against multi-modality methods with 59% number of parameters less.
Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving. Existing pre-training methods either rely on expensive supervised learning with 3D annotations, limiting the scalability, or focus on single-frame or monocular inputs, neglecting the temporal information. We propose MIM4D, a novel pre-training paradigm based on dual masked image modeling (MIM). MIM4D leverages both spatial and temporal relations by training on masked multi-view video inputs. It constructs pseudo-3D features using continuous scene flow and projects them onto 2D plane for supervision. To address the lack of dense 3D supervision, MIM4D reconstruct pixels by employing 3D volumetric differentiable rendering to learn geometric representations. We demonstrate that MIM4D achieves state-of-the-art performance on the nuScenes dataset for visual representation learning in autonomous driving. It significantly improves existing methods on multiple downstream tasks, including BEV segmentation (8.7% IoU), 3D object detection (3.5% mAP), and HD map construction (1.4% mAP). Our work offers a new choice for learning representation at scale in autonomous driving. Code and models are released at https://github.com/hustvl/MIM4D
Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem. It significantly reduces human labeling costs and traditionally relies on multi-instance learning and pseudo-labeling. This paper introduces WeakSAM and solves the weakly-supervised object detection (WSOD) and segmentation by utilizing the pre-learned world knowledge contained in a vision foundation model, i.e., the Segment Anything Model (SAM). WeakSAM addresses two critical limitations in traditional WSOD retraining, i.e., pseudo ground truth (PGT) incompleteness and noisy PGT instances, through adaptive PGT generation and Region of Interest (RoI) drop regularization. It also addresses the SAM's problems of requiring prompts and category unawareness for automatic object detection and segmentation. Our results indicate that WeakSAM significantly surpasses previous state-of-the-art methods in WSOD and WSIS benchmarks with large margins, i.e. average improvements of 7.4% and 8.5%, respectively. The code is available at \url{https://github.com/hustvl/WeakSAM}.
Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging. In this work, to cope with the uncertainty problem, we propose VADv2, an end-to-end driving model based on probabilistic planning. VADv2 takes multi-view image sequences as input in a streaming manner, transforms sensor data into environmental token embeddings, outputs the probabilistic distribution of action, and samples one action to control the vehicle. Only with camera sensors, VADv2 achieves state-of-the-art closed-loop performance on the CARLA Town05 benchmark, significantly outperforming all existing methods. It runs stably in a fully end-to-end manner, even without the rule-based wrapper. Closed-loop demos are presented at https://hgao-cv.github.io/VADv2.
The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools. However, their reliance on predefined and trained object categories limits their applicability in open scenarios. Addressing this limitation, we introduce YOLO-World, an innovative approach that enhances YOLO with open-vocabulary detection capabilities through vision-language modeling and pre-training on large-scale datasets. Specifically, we propose a new Re-parameterizable Vision-Language Path Aggregation Network (RepVL-PAN) and region-text contrastive loss to facilitate the interaction between visual and linguistic information. Our method excels in detecting a wide range of objects in a zero-shot manner with high efficiency. On the challenging LVIS dataset, YOLO-World achieves 35.4 AP with 52.0 FPS on V100, which outperforms many state-of-the-art methods in terms of both accuracy and speed. Furthermore, the fine-tuned YOLO-World achieves remarkable performance on several downstream tasks, including object detection and open-vocabulary instance segmentation.
Recently the state space models (SSMs) with efficient hardware-aware designs, i.e., Mamba, have shown great potential for long sequence modeling. Building efficient and generic vision backbones purely upon SSMs is an appealing direction. However, representing visual data is challenging for SSMs due to the position-sensitivity of visual data and the requirement of global context for visual understanding. In this paper, we show that the reliance of visual representation learning on self-attention is not necessary and propose a new generic vision backbone with bidirectional Mamba blocks (Vim), which marks the image sequences with position embeddings and compresses the visual representation with bidirectional state space models. On ImageNet classification, COCO object detection, and ADE20k semantic segmentation tasks, Vim achieves higher performance compared to well-established vision transformers like DeiT, while also demonstrating significantly improved computation & memory efficiency. For example, Vim is 2.8$\times$ faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on images with a resolution of 1248$\times$1248. The results demonstrate that Vim is capable of overcoming the computation & memory constraints on performing Transformer-style understanding for high-resolution images and it has great potential to become the next-generation backbone for vision foundation models. Code is available at https://github.com/hustvl/Vim.
Neural Radiances Fields (NeRF) and their extensions have shown great success in representing 3D scenes and synthesizing novel-view images. However, most NeRF methods take in low-dynamic-range (LDR) images, which may lose details, especially with nonuniform illumination. Some previous NeRF methods attempt to introduce high-dynamic-range (HDR) techniques but mainly target static scenes. To extend HDR NeRF methods to wider applications, we propose a dynamic HDR NeRF framework, named HDR-HexPlane, which can learn 3D scenes from dynamic 2D images captured with various exposures. A learnable exposure mapping function is constructed to obtain adaptive exposure values for each image. Based on the monotonically increasing prior, a camera response function is designed for stable learning. With the proposed model, high-quality novel-view images at any time point can be rendered with any desired exposure. We further construct a dataset containing multiple dynamic scenes captured with diverse exposures for evaluation. All the datasets and code are available at \url{https://guanjunwu.github.io/HDR-HexPlane/}.
Synthesizing multi-view 3D from one single image is a significant and challenging task. For this goal, Zero-1-to-3 methods aim to extend a 2D latent diffusion model to the 3D scope. These approaches generate the target-view image with a single-view source image and the camera pose as condition information. However, the one-to-one manner adopted in Zero-1-to-3 incurs challenges for building geometric and visual consistency across views, especially for complex objects. We propose a cascade generation framework constructed with two Zero-1-to-3 models, named Cascade-Zero123, to tackle this issue, which progressively extracts 3D information from the source image. Specifically, a self-prompting mechanism is designed to generate several nearby views at first. These views are then fed into the second-stage model along with the source image as generation conditions. With self-prompted multiple views as the supplementary information, our Cascade-Zero123 generates more highly consistent novel-view images than Zero-1-to-3. The promotion is significant for various complex and challenging scenes, involving insects, humans, transparent objects, and stacked multiple objects etc. The project page is at https://cascadezero123.github.io/.