Animation News

arXiv cs.GR details DSD, a diffusion-based skill discovery method that learns a wider set of reusable humanoid motor skills. For game teams building animation or AI-driven characters, the pitch is …

EMODY Flow tackles a common failure in audio-driven character animation: emotion labels get ignored, and motion collapses toward the same result. The 35M-parameter system couples a frozen Qwen-3 Omni backbone …

ATOP is a new 3D part-articulation method that lets creators drive object motion from text and personalize it with motion examples. For game teams, that points to faster iteration on …

Researchers have introduced DMP, a motion-retargeting method that lets animators steer character movement more directly while preserving the source performance. The technique uses motion paraphrasing to adapt animation across different …

A new motion-generation system aims to cover both humans and animals with one model, sidestepping the topology mismatch that usually forces separate pipelines. UniMo pairs a point-cloud representation with dynamic …

ReCHOIR targets a stubborn retargeting problem: preserving object interaction when the same motion lands on different humanoid rigs. The method uses contact cues and a part-aware latent space to keep …

A new muscle-driven simulation pipeline can generate realistic sprinting and drill motions without motion-capture demonstrations. Running at up to 1000x real time on a single GPU, it trains control policies …

InstantMimic pushes physics-based character training into the seconds range by moving the entire RL loop onto the GPU. The system targets imitation-driven motion control, cutting out CPU bottlenecks and fragmented …

A new pre-production review system called MOONWALK targets one of animation and VFX’s chronic pain points: keeping junior artists, supervisors, and changing briefs aligned. It structures intent, evidence, and action …

STyMo can learn a motion style from only seconds of paired data and train in one to two minutes, making style transfer far more practical for character animation. The system …

UniMate aims to remove a major bottleneck in character animation: motion generation for arbitrary rigs. The model takes a rigged 3D asset and a text prompt, then produces articulated motion …

Onimusha: Way of the Sword leans hard into swordplay systems that reward timing, not just aggression. Parry, deflect, Issen, Blade Barrage, Blade Lock, and Reflex Dodge all feed into stamina, …

A new GPU multibody solver reformulates constrained dynamics as affine bodies linked by peridynamic bonds, aiming to handle rigid bodies, flexible joints, contact, and friction in real time. The method …

A new humanoid retargeting system uses learned point-cloud correspondence to map human motion onto robots without hand-built keypoint pairs. That matters for teams training embodied agents: it promises denser pose …

A new rigging workflow turns hand-drawn contour strokes into high-level character pose parameters, aiming to cut the trial-and-error loop in stylized animation. The method uses a differentiable MLP surrogate for …

SILENT HILL f is taking the series into melee-only combat, a sharp shift for a horror franchise long associated with firearms and survival tension. That design choice forces every encounter …

GamesIndustry.biz reports Rockstar has formed a new Los Angeles team to art-direct more realistic NPCs for Grand Theft Auto 6. The studio says GTA 6 will ship with over 600,000 …

Persona 4 Revival is being rebuilt as a modern remake that keeps the original’s themes intact while overhauling visuals, animation, and presentation. ATLUS says the goal is not to make …

Procedural GPU noise can look fine spatially and still pulse badly over time. By folding time into the hash as a third dimension, each octave changes in lockstep, and with …

SeMoCo reframes motion tokens around meaning first, splitting each token into a semantic core and residual kinematics. For animation and ML pipelines, that could make text-to-motion generation easier to steer …