Related papers: VGGT: Visual Geometry Grounded Transformer
3D visual grounding aims to localize the unique target described by natural languages in 3D scenes. The significant gap between 3D and language modalities makes it a notable challenge to distinguish multiple similar objects through the…
Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer…
The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as an efficient and effective alternative to full fine-tuning…
We present Generalizable NeRF Transformer (GNT), a transformer-based architecture that reconstructs Neural Radiance Fields (NeRFs) and learns to renders novel views on the fly from source views. While prior works on NeRFs optimize a scene…
In this work, we aim to improve the 3D reasoning ability of Transformers in multi-view 3D human pose estimation. Recent works have focused on end-to-end learning-based transformer designs, which struggle to resolve geometric information…
Dense visual odometry (VO), which provides pose estimation and dense 3D reconstruction, serves as the cornerstone for applications ranging from robotics to augmented reality. Recently, feed-forward models have demonstrated remarkable…
3D Gaussian Splatting (3DGS) has recently unlocked real-time, high-fidelity novel view synthesis by representing scenes using explicit 3D primitives. However, traditional methods often require millions of Gaussians to capture complex…
We present Gen3R, a method that bridges the strong priors of foundational reconstruction models and video diffusion models for scene-level 3D generation. We repurpose the VGGT reconstruction model to produce geometric latents by training an…
In this work, we explore neat yet effective Transformer-based frameworks for visual grounding. The previous methods generally address the core problem of visual grounding, i.e., multi-modal fusion and reasoning, with manually-designed…
Reliable 3D reconstruction from in-the-wild image collections is often hindered by "noisy" images-irrelevant inputs with little or no view overlap with others. While traditional Structure-from-Motion pipelines handle such cases through…
Visual Geometry Transformer (VGGT) is a strong feed-forward model for multiple 3D tasks, but its Alternating-Attention (AA) stack scales quadratically in the total token count, making long clips expensive. Existing token-reduction…
Generalizing a pretrained model to unseen datasets without retraining is an essential step toward a foundation model. However, achieving such cross-dataset, fully inductive inference is difficult in graph-structured data where feature…
3D Visual Grounding (3DVG) is an essential capability for embodied AI, requiring agents to localize objects in 3D scenes based on natural language descriptions. Recent zero-shot methods leverage 2D vision-language models (LVLMs). However,…
Visual Grounding (VG) aims to locate the most relevant region in an image, based on a flexible natural language query but not a pre-defined label, thus it can be a more useful technique than object detection in practice. Most…
Generation of 3D data by deep neural network has been attracting increasing attention in the research community. The majority of extant works resort to regular representations such as volumetric grids or collection of images; however, these…
Deep neural network representations align well with brain activity in the ventral visual stream. However, the primate visual system has a distinct dorsal processing stream with different functional properties. To test if a model trained to…
Various stuff and things in visual data possess specific traits, which can be learned by deep neural networks and are implicitly represented as the visual prior, e.g., object location and shape, in the model. Such prior potentially impacts…
Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…
Holistic 3D scene understanding involves capturing and parsing unstructured 3D environments. Due to the inherent complexity of the real world, existing models have predominantly been developed and limited to be task-specific. We introduce…
Event cameras offer promising advantages such as high dynamic range and low latency, making them well-suited for challenging lighting conditions and fast-moving scenarios. However, reconstructing 3D scenes from raw event streams is…