pith. sign in

arxiv: 2505.04831 · v2 · pith:2VE6CKAAnew · submitted 2025-05-07 · 💻 cs.RO · cs.GR· cs.LG

Steerable Scene Generation with Post Training and Inference-Time Search

classification 💻 cs.RO cs.GRcs.LG
keywords scenetrainingdataenvironmentsgenerationinference-timemodelscenes
0
0 comments X
read the original abstract

Training robots in simulation requires diverse 3D scenes that reflect the specific challenges of downstream tasks. However, scenes that satisfy strict task requirements, such as high-clutter environments with plausible spatial arrangement, are rare and costly to curate manually. Instead, we generate large-scale scene data using procedural models that approximate realistic environments for robotic manipulation, and adapt it to task-specific goals. We do this by training a unified diffusion-based generative model that predicts which objects to place from a fixed asset library, along with their SE(3) poses. This model serves as a flexible scene prior that can be adapted using reinforcement learning-based post training, conditional generation, or inference-time search, steering generation toward downstream objectives even when they differ from the original data distribution. Our method enables goal-directed scene synthesis that respects physical feasibility and scales across scene types. We introduce a novel MCTS-based inference-time search strategy for diffusion models, enforce feasibility via projection and simulation, and release a dataset of over 44 million SE(3) scenes spanning five diverse environments. Website with videos, code, data, and model weights: https://steerable-scene-generation.github.io/

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics

    cs.RO 2026-06 unverdicted novelty 7.0

    Ambient Diffusion Policy enables better imitation learning from suboptimal robot data by leveraging spectral properties to restrict data usage to specific diffusion times.

  2. STABLE: Simulation-Ready Tabletop Layout Generation via a Semantics-Physics Dual System

    cs.CV 2026-05 unverdicted novelty 6.0

    STABLE generates simulation-ready tabletop scenes by alternating a semantic LLM reasoner for task-aligned coarse layouts with a physics corrector for physical plausibility using progressive scene expansion.