Related papers: Multi-view Pyramid Transformer: Look Coarser to Se…
Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of…
The 3D visual grounding task aims to ground a natural language description to the targeted object in a 3D scene, which is usually represented in 3D point clouds. Previous works studied visual grounding under specific views. The…
Real-time rendering and animation of humans is a core function in games, movies, and telepresence applications. Existing methods have a number of drawbacks we aim to address with our work. Triangle meshes have difficulty modeling thin…
Recent volumetric 3D reconstruction methods can produce very accurate results, with plausible geometry even for unobserved surfaces. However, they face an undesirable trade-off when it comes to multi-view fusion. They can fuse all available…
In human-centered environments such as restaurants, homes, and warehouses, robots often face challenges in accurately recognizing 3D objects. These challenges stem from the complexity and variability of these environments, including diverse…
Multi-view inverse rendering aims to recover geometry, materials, and illumination consistently across multiple viewpoints. When applied to multi-view images, existing single-view approaches often ignore cross-view relationships, leading to…
Perception is a fundamental task in the field of computer vision, encompassing a diverse set of subtasks that can be systematically categorized into four distinct groups based on two dimensions: prediction type and instruction type.…
Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been…
n this paper, we propose an effective and efficient pyramid multi-view stereo (MVS) net with self-adaptive view aggregation for accurate and complete dense point cloud reconstruction. Different from using mean square variance to generate…
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of…
Although neural radiance fields (NeRF) have shown impressive advances for novel view synthesis, most methods typically require multiple input images of the same scene with accurate camera poses. In this work, we seek to substantially reduce…
In video surveillance, pedestrian retrieval (also called person re-identification) is a critical task. This task aims to retrieve the pedestrian of interest from non-overlapping cameras. Recently, transformer-based models have achieved…
We propose a scene-level inverse rendering framework that uses multi-view images to decompose the scene into geometry, a SVBRDF, and 3D spatially-varying lighting. Because multi-view images provide a variety of information about the scene,…
A central challenge of video prediction lies where the system has to reason the objects' future motions from image frames while simultaneously maintaining the consistency of their appearances across frames. This work introduces an…
We propose a learning-based approach for novel view synthesis for multi-camera 360$^{\circ}$ panorama capture rigs. Previous work constructs RGBD panoramas from such data, allowing for view synthesis with small amounts of translation, but…
Recent advances in large language models (LLMs) have shown impressive performance in passage reranking tasks. Despite their success, LLM-based methods still face challenges in efficiency and sensitivity to external biases. (1) Existing…
Recovering the shape and appearance of real-world objects from natural 2D images is a long-standing and challenging inverse rendering problem. In this paper, we introduce a novel hybrid differentiable rendering method to efficiently…
In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional information carried by 2D feature representations, unlike…
A central goal of visual recognition is to understand objects and scenes from a single image. 2D recognition has witnessed tremendous progress thanks to large-scale learning and general-purpose representations. Comparatively, 3D poses new…
Dense prediction in medical volume provides enriched guidance for clinical analysis. CNN backbones have met bottleneck due to lack of long-range dependencies and global context modeling power. Recent works proposed to combine vision…