Tag
Scene-Designer 提出一个通过设计与批评双重经验学习设计智能的智能体框架，用于生成完整、连贯且可用的 3D 室内场景，并提出 Critic 引导的 Scene-GRPO 方法，在物理有效性、功能正确性和布局连贯性上取得更优性能。
Tetris3D proposes a generative framework for single-image 3D scene reconstruction that conditions each object's shape and pose on surrounding geometry and physical relationships, along with ComOb, a 1.2M-scene physics-simulation dataset, achieving state-of-the-art physical stability and coherent multi-object reconstruction.
SPAR3S is a sparse auto-regressive generative model that efficiently generates complete 3D scenes from sparse multi-view images without requiring 3D ground truth data, using a voxel-aligned latent space and differentiable 3D Gaussian Splatting.
A paper from the DUSt3R team proposes sparse auto-regressive modeling for 3D scene generation from multi-view images, using a voxel-aligned 3D latent space and an occupancy-aware masked autoregressive transformer.
SceneFrom3D is a framework that automatically schedules views from input geometry to generate high-quality outdoor 3D scenes with object-level control over appearance and geometry adherence.
CGGS is a text-to-3D framework that improves geometric consistency and quality in ego-centric 3D scene generation using a multi-stage approach with consistency-augmented loss, layout decoration, and geometric refinement via entropy-based depth loss.