18 items across game development
18 results
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 rigging approach for Gaussian splats uses differentiable skinning weights to avoid the holes and stretching artifacts that show up when points are only moved rigidly. The method stays …
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 …
Biharmonic skinning just got a mesh-free path that can handle open surfaces, triangle soups, and point clouds without tetrahedralization failures. The new method uses geometric fields and hardware ray tracing …
A new rigging study shows autoregressive character models can be pushed beyond humanoids and into plant reconstruction. Using UniRig and SkinTokens as a starting point, the researchers found branch topology …
Nova3D turns 3D asset generation into executable Blender code instead of a sealed mesh. The system produced valid outputs for all 54 benchmark items, with named parts, assembly trees, numeric …
RegHead tackles a stubborn character-tech problem: building usable blendshape sets for non-humanoid heads without expensive per-asset optimization. The system pairs a shared expression vocabulary with feed-forward registration, aiming to retarget …
TopoCap tackles a real production pain point: retargeting motion from monocular video onto rigs that don’t share a human template. The paper claims zero-shot animation transfer across arbitrary skeletal topologies, …
RigPAPR tackles a common failure mode in neural character animation: joint-boundary artifacts when Gaussian splats are driven by rigid skinning. The paper claims a static PAPR point cloud can be …
A new paper shows sketch input can drive articulation modeling for CAD objects, automatically finding movable parts and their motion from simple 2D arrows and strokes. For game teams, the …
A new rigging paper tackles a familiar pain point: auto-rigged characters often have no real pose-space model, so random sampling or manual tweaking can produce broken joints and ugly self-intersections. …
The introduction of the Skelebones rigging system represents a significant advancement for graphics programmers and animators. By effectively capturing non-rigid deformations while maintaining intuitive control, this method improves reanimation performance …
SPRig introduces a significant advancement in rigging technology, allowing for pose-invariant rigs from dynamic mesh sequences. This is particularly relevant for graphics programmers and artists who often face challenges with …
The introduction of SkinTokens revolutionizes rigging in 3D animation, offering a 98%-133% improvement in skinning accuracy. This advancement is crucial for artists and programmers, streamlining workflows and enhancing fidelity in …
RigMo introduces a groundbreaking approach to generative animation by unifying rig and motion learning, eliminating the need for manual rig annotations. This innovation allows for more scalable and interpretable animation …
TexAvatars introduces a hybrid approach to creating photorealistic 3D head avatars, significantly improving rigging stability. This advancement is particularly relevant for graphics programmers and artists, as it enhances the fidelity …
The new Rigging in UE 5.6 Workshop is now available for free, providing essential skills for artists and animators. This resource will help you create animation-friendly rigs, enhancing your workflow …
The new Rigging in UE Control Rig Workshop is now available for free, providing a valuable resource for artists and animators looking to enhance their rigging skills. This workshop allows …
With your permission, GameDev.net uses analytics cookies to understand how people use the platform. You can accept analytics or continue with necessary cookies only. Learn more
