Related papers: SViM3D: Stable Video Material Diffusion for Single…
Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…
Despite the advances in the field of generative models in computer vision, video stabilization still lacks a pure regressive deep-learning-based formulation. Deep video stabilization is generally formulated with the help of explicit motion…
Structure-from-Motion (SfM), a task aiming at jointly recovering camera poses and 3D geometry of a scene given a set of images, remains a hard problem with still many open challenges despite decades of significant progress. The traditional…
Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require…
We present a novel video generation framework that integrates 3-dimensional geometry and dynamic awareness. To achieve this, we augment 2D videos with 3D point trajectories and align them in pixel space. The resulting 3D-aware video…
Volumetric video enables immersive experiences by capturing dynamic 3D scenes, enabling diverse applications for virtual reality, education, and telepresence. However, traditional methods struggle with fixed lighting conditions, while…
Novel view synthesis (NVS) boosts immersive experiences in computer vision and graphics. Existing techniques, though progressed, rely on dense multi-view observations, restricting their application. This work takes on the challenge of…
Decomposing physically-based materials from images into their constituent properties remains challenging, particularly when maintaining both computational efficiency and physical consistency. While recent diffusion-based approaches have…
We present a novel approach to the generation of static and articulated 3D assets that has a 3D autodecoder at its core. The 3D autodecoder framework embeds properties learned from the target dataset in the latent space, which can then be…
Real-world video super-resolution (VSR) presents significant challenges due to complex and unpredictable degradations. Although some recent methods utilize image diffusion models for VSR and have shown improved detail generation…
Although powerful for image generation, consistent and controllable video is a longstanding problem for diffusion models. Video models require extensive training and computational resources, leading to high costs and large environmental…
A recent frontier in computer vision has been the task of 3D video generation, which consists of generating a time-varying 3D representation of a scene. To generate dynamic 3D scenes, current methods explicitly model 3D temporal dynamics by…
Active object reconstruction is crucial for many robotic applications. A key aspect in these scenarios is generating object-specific view configurations to obtain informative measurements for reconstruction. One-shot view planning enables…
Recent unified 3D generation models have made remarkable progress in producing high-quality 3D assets from a single image. Notably, layout-aware approaches such as SAM3D can reconstruct multiple objects while preserving their spatial…
Video generation has achieved remarkable progress with the introduction of diffusion models, which have significantly improved the quality of generated videos. However, recent research has primarily focused on scaling up model training,…
The ability to generate virtual environments is crucial for applications ranging from gaming to physical AI domains such as robotics, autonomous driving, and industrial AI. Current learning-based 3D reconstruction methods rely on the…
Reconstructing 3D assets from images has long required separate pipelines for geometry reconstruction, material estimation, and illumination recovery, each with distinct limitations and computational overhead. We present ReLi3D, the first…
Recent months have witnessed rapid progress in 3D generation based on diffusion models. Most advances require fine-tuning existing 2D Stable Diffsuions into multi-view settings or tedious distilling operations and hence fall short of 3D…
Novel view synthesis (NVS) is a cornerstone for image-to-3d creation. However, existing works still struggle to maintain consistency between the generated views and the input views, especially when there is a significant camera pose…
Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To…