Related papers: MapAnything: Universal Feed-Forward Metric 3D Reco…
Posing 3D characters is a fundamental task in computer graphics. However, existing paradigms, ranging from traditional auto-rigging to recent pose-conditioned generative models, frequently struggle with inaccurate skinning weights, fixed…
Grounding referring expressions in RGBD image has been an emerging field. We present a novel task of 3D visual grounding in single-view RGBD image where the referred objects are often only partially scanned due to occlusion. In contrast to…
Holistic 3D scene understanding, which jointly models geometry, appearance, and semantics, is crucial for applications like augmented reality and robotic interaction. Existing feed-forward 3D scene understanding methods (e.g., LSM) are…
Understanding and reconstructing the complex geometry and motion of dynamic scenes from video remains a formidable challenge in computer vision. This paper introduces D4RT, a simple yet powerful feedforward model designed to efficiently…
Depth images have a wide range of applications, such as 3D reconstruction, autonomous driving, augmented reality, robot navigation, and scene understanding. Commodity-grade depth cameras are hard to sense depth for bright, glossy,…
Depth imaging has largely focused on sensor and intrinsics properties. However, the accuracy of acquire pixel is largely dependent on the capture. We propose a new depth estimation and approximation algorithm which takes an arbitrary 3D…
Feed-forward 3D modeling has emerged as a promising approach for rapid and high-quality 3D reconstruction. In particular, directly generating explicit 3D representations, such as 3D Gaussian splatting, has attracted significant attention…
Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous driving and robotics. Compared to the complex, multi-modal systems deployed today, multi-camera systems provide a simpler, low-cost alternative. However,…
Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plug-and-play and diffusion methods leveraging pretrained denoisers, and unrolled architectures…
Feed-forward 3D reconstruction for autonomous driving has advanced rapidly, yet existing methods struggle with the joint challenges of sparse, non-overlapping camera views and complex scene dynamics. We present UniSplat, a general…
Reconstructing large-scale urban scenes from sparse aerial views is a crucial yet challenging task. Due to biased top-down and shallow-oblique camera poses, sparse aerial captures exhibit strong evidence imbalance: roofs and open regions…
We present a user-friendly image editing system that supports a drag-and-drop object insertion (where the user merely drags objects into the image, and the system automatically places them in 3D and relights them appropriately),…
We present Fillerbuster, a unified model that completes unknown regions of a 3D scene with a multi-view latent diffusion transformer. Casual captures are often sparse and miss surrounding content behind objects or above the scene. Existing…
Inferring 3D structure of a generic object from a 2D image is a long-standing objective of computer vision. Conventional approaches either learn completely from CAD-generated synthetic data, which have difficulty in inference from real…
With recent advances, Feed-forward Reconstruction Models (FFRMs) have demonstrated great potential in reconstruction quality and adaptiveness to multiple downstream tasks. However, the excessive reliance on multi-view geometric annotations,…
3D human reconstruction and animation are long-standing topics in computer graphics and vision. However, existing methods typically rely on sophisticated dense-view capture and/or time-consuming per-subject optimization procedures. To…
Estimating 3D geometry from monocular colonoscopy images is challenging due to non-Lambertian surfaces, moving light sources, and large textureless regions. While recent 3D geometric foundation models eliminate the need for multi-stage…
Recovering the metric 3D shape from a single image is particularly relevant for robotics and embodied intelligence applications, where accurate spatial understanding is crucial for navigation and interaction with environments. Usually, the…
Image-based 3D object modeling refers to the process of converting raw optical images to 3D digital representations of the objects. Very often, such models are desired to be dimensionally true, semantically labeled with photorealistic…
Recently, deep learning-based 3D face reconstruction methods have demonstrated promising advancements in terms of quality and efficiency. Nevertheless, these techniques face challenges in effectively handling occluded scenes and fail to…