REVIEW 6 cited by
InterMask: 3D Human Interaction Generation via Collaborative Masked Modeling
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Generating realistic 3D human-human interactions from textual descriptions remains a challenging task. Existing approaches, typically based on diffusion models, often produce results lacking realism and fidelity. In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space. InterMask first employs a VQ-VAE to transform each motion sequence into a 2D discrete motion token map. Unlike traditional 1D VQ token maps, it better preserves fine-grained spatio-temporal details and promotes spatial awareness within each token. Building on this representation, InterMask utilizes a generative masked modeling framework to collaboratively model the tokens of two interacting individuals. This is achieved by employing a transformer architecture specifically designed to capture complex spatio-temporal inter-dependencies. During training, it randomly masks the motion tokens of both individuals and learns to predict them. For inference, starting from fully masked sequences, it progressively fills in the tokens for both individuals. With its enhanced motion representation, dedicated architecture, and effective learning strategy, InterMask achieves state-of-the-art results, producing high-fidelity and diverse human interactions. It outperforms previous methods, achieving an FID of $5.154$ (vs $5.535$ of in2IN) on the InterHuman dataset and $0.399$ (vs $5.207$ of InterGen) on the InterX dataset. Additionally, InterMask seamlessly supports reaction generation without the need for model redesign or fine-tuning.
Forward citations
Cited by 6 Pith papers
-
MoRAE: Flow-Friendly Self-Supervised Latents for Text-to-Motion Generation
Distilling frozen Motion-JEPA features into a compact 32-D latent whose geometry is coupled to the decoder lets a standard non-autoregressive flow-matching DiT reach state-of-the-art text-to-motion quality on HumanML3...
-
MIME: Multimodal Interactive Motion Encoder
MIME, a co-attention encoder with explicit relational features and curriculum contrastive training, improves two-person text-motion retrieval and transfers to downstream generation.
-
MoLingo: Motion-Language Alignment for Text-to-Human Motion Generation
A semantically aligned latent space plus multi-token cross-attention conditioning sets a new state of the art in text-to-human-motion generation on HumanML3D.
-
PhysiInter: Integrating Physical Mapping for High-Fidelity Human Interaction Generation
A text-to-motion pipeline that projects motions through physics-based imitation for training and post-processing, plus new consistency and marker-interaction losses.
-
TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging
A 0.5B VLA with bridge-conditioned discrete diffusion and 2D temporal–spatial action masking reaches 95.7% LIBERO success and 4.19 CALVIN average length.
-
Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis
Human-X jointly predicts actions and reactions in real time to produce physically plausible human-machine interaction motion.
Discussion (0). Sign in to comment.