AI Paper Atlas

Research map / 3D vision / 3D generation

Generating Human Interaction Motions in Scenes with Text Control

Hongwei Yi, Justus Thies, Michael J. Black, Xue Bin Peng, Davis Rempe

ECCV 2024 · 3D vision › 3D generation · approach: Scene-aware human motion synthesis · 52 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pre-train scene-agnostic branch then fine-tune scene-aware branch instead of 1-stage training (ablation)TeSMo navigation · Loco-3D-FRONTRoot position error (m): 0.197 -> 0.169Improved
pre-train then fine-tune instead of 1-stage training (ablation)TeSMo navigation · Loco-3D-FRONTR-precision (top-3): 0.152 -> 0.376Improved
use two-branch architecture instead of single-branch TRACE-style floor map input (ablation)TeSMo navigation · Loco-3D-FRONTCollision ratio: 0.055 -> 0.031Improved
two-stage pelvis trajectory then in-painting instead of one-stage full-body generation (ablation)TeSMo navigation · Loco-3D-FRONTRoot position error (m): 0.844 -> 0.169Improved
use PriorMDM in-painting instead of OmniControl in-painting (ablation)TeSMo navigation · Loco-3D-FRONTRoot position error (m): 0.459 -> 0.169Improved
use OmniControl in-painting instead of PriorMDM (ablation)TeSMo navigation · Loco-3D-FRONTFID (full-body): 20.465 -> 17.927Improved
add goal-reaching test-time guidance (ablation)TeSMo navigation · Loco-3D-FRONTGoal position error: 0.1568 -> 0.118Improved
add collision test-time guidance (ablation)TeSMo navigation · Loco-3D-FRONTCollision ratio: 0.0294 -> 0.0013Improved
add goal-reaching guidance without collision guidance (ablation)TeSMo navigation · Loco-3D-FRONTCollision ratio: 0.0294 -> 0.0342Hurt
add collision guidance to interaction model (ablation)TeSMo interaction · SAMP sittingPenetration ratio: 0.0611 -> 0.0414Improved
add goal-reaching guidance to interaction model (ablation)TeSMo interaction · SAMP sittingGoal position error: 0.1445 -> 0.1453No clear effect
use TeSMo diffusion model instead of RL-based DIMOSTeSMo interaction · SAMP sittingGoal position error: 0.2020 -> 0.1445Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy