Papers › BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis

BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis

28 Nov 2024arXiv:2412.00112archive 2025-07-28

Seong-Eun Hong, Soobin Lim, Juyeong Hwang, Minwook Chang, Hyeongyeop Kang

Generating natural and expressive human motions from textual descriptions is challenging due to the complexity of coordinating full-body dynamics and capturing nuanced motion patterns over extended sequences that accurately reflect the given text. To address this, we introduce BiPO, Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis, a novel model that enhances text-to-motion synthesis by integrating part-based generation with a bidirectional autoregressive architecture. This integration allows BiPO to consider both past and future contexts during generation while enhancing detailed control over individual body parts without requiring ground-truth motion length. To relax the interdependency among body parts caused by the integration, we devise the Partial Occlusion technique, which probabilistically occludes the certain motion part information during training. In our comprehensive experiments, BiPO achieves state-of-the-art performance on the HumanML3D dataset, outperforming recent methods such as ParCo, MoMask, and BAMM in terms of FID scores and overall motion quality. Notably, BiPO excels not only in the text-to-motion generation task but also in motion editing tasks that synthesize motion based on partially generated motion sequences and textual descriptions. These results reveal the BiPO's effectiveness in advancing text-to-motion synthesis and its potential for practical applications.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Motion GenerationMotion Synthesis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Motion Synthesis HumanML3D BiPO Diversity 9.556 #3 of 37 Archive leaderboard report
Motion Synthesis HumanML3D BiPO FID 0.030 #3 of 37 Archive leaderboard report
Motion Synthesis HumanML3D BiPO Multimodality 1.374 #3 of 37 Archive leaderboard report
Motion Synthesis HumanML3D BiPO R Precision Top3 0.809 #3 of 37 Archive leaderboard report
Motion Synthesis KIT Motion-Language BiPO Diversity 10.833 #4 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language BiPO FID 0.164 #4 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language BiPO Multimodality 1.098 #4 of 31 Archive leaderboard report
Motion Synthesis KIT Motion-Language BiPO R Precision Top3 0.803 #4 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections