Related papers: One2Scene: Geometric Consistent Explorable 3D Scen…
Understanding and modeling the 3D scene from a single image is a practical problem. A recent advance proposes a panoptic 3D scene reconstruction task that performs both 3D reconstruction and 3D panoptic segmentation from a single image.…
Existing single-view 3D generative models typically adopt multiview diffusion priors to reconstruct object surfaces, yet they remain prone to inter-view inconsistencies and are unable to faithfully represent complex internal structure or…
Sparse-view 3D modeling represents a fundamental tension between reconstruction fidelity and generative plausibility. While feed-forward reconstruction excels in efficiency and input alignment, it often lacks the global priors needed for…
Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative…
Recent advancements in Generative Artificial Intelligence (GenAI) have significantly enhanced the capabilities of both image generation and editing. However, current approaches often treat these tasks separately, leading to inefficiencies…
We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance. Existing methods face key challenges: 2D-lifting approaches suffer from geometric…
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are…
Being able to edit panoramic images is crucial for creating realistic 360{\deg} visual experiences. However, existing perspective-based image editing methods fail to model the spatial structure of panoramas. Conventional cube-map…
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provide minimal physical control, and single-image-to-3D…
Generating realistic 3D indoor scenes from user inputs remains a challenging problem in computer vision and graphics, requiring careful balance of geometric consistency, spatial relationships, and visual realism. While neural generation…
Understanding 3D scenes from a single image is fundamental to a wide variety of tasks, such as for robotics, motion planning, or augmented reality. Existing works in 3D perception from a single RGB image tend to focus on geometric…
Interactive 3D scene generation from a single image has gained significant attention due to its potential to create immersive virtual worlds. However, a key challenge in current 3D generation methods is the limited explorability, which…
The precise reconstruction of 3D objects from a single RGB image in complex scenes presents a critical challenge in virtual reality, autonomous driving, and robotics. Existing neural implicit 3D representation methods face significant…
Generating complete 3D objects under partial occlusions (i.e., amodal scenarios) is a practically important yet challenging problem, as large portions of object geometry are unobserved in real-world scenarios. Existing approaches either…
Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a…
3D scene generation is in high demand across various domains, including virtual reality, gaming, and the film industry. Owing to the powerful generative capabilities of text-to-image diffusion models that provide reliable priors, the…
Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory for consistency, or iterative 3D reconstruction and…
MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense geometry and semantics of a scene are inferred from a single monocular RGB image. Different from the SSC literature, relying on 2.5 or 3D input, we solve the…
View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object…
We introduce VividDream, a method for generating explorable 4D scenes with ambient dynamics from a single input image or text prompt. VividDream first expands an input image into a static 3D point cloud through iterative inpainting and…