Find and compare the top AI tools for 3D. Browse features, pricing, and user ratings of all the AI tools and apps in the market.
Newest
ReLift reconstructs dense 3D point trajectories from a monocular video. It combines the output of a 2D tracker with a video geometry estimator to recover how points move in spac
HairDeck turns a character image into stylized 3D hair cards for animation and avatar workflows. It produces a set of textured strips that follow the overall silhouette and the
FlowHMR reconstructs 3D human motion from monocular video. It targets motion that can be tracked in a physics simulation and provides tools to preview the recovered sequence and
CoLa3D reconstructs an object-composed 3D scene from a single image. It outputs individual meshes that share a coordinate frame so the resulting objects can be inspected and man
SceneBloom creates realistic indoor environments for training embodied agents. It translates room descriptions into varied furniture layouts and simulation-ready scenes, coverin
PhysAg3D turns an object image into a detailed 3D asset with object-specific interactions. It combines generated appearance and geometry with reasoning about parts, joints, and
IDOL converts a single object image into a three-dimensional Gaussian splat. It accepts photographs, rendered objects, and generated images, reconstructing a viewable asset that
PURE reconstructs depth, camera poses, and colored 3D point clouds from video clips or image sequences. Its unlabeled post-training approach improves feed-forward reconstruction
Kimi K3.1 Pro is Moonshot AI's large-context model for coding, 3D creation, financial research, and complex agentic work. It is a post-trained Kimi K3 model in the 3T class, usi
Hi3D 1.0 is a publicly released image-to-3D model, formerly called Sparc3D, for turning reference imagery into detailed 3D assets. The model builds on training with nearly two m
Viggle JST-2 is a physics-native world foundation model for generating scenes, characters, and their motion. It represents persistent matter as 3D atoms with explicit positions
InfiniSplat v2 reconstructs 3D Gaussian scenes from arbitrary collections of input views. Its dual-branch architecture freezes geometry while learning Gaussian attributes, using
GaussiAnimate rigs and animates reconstructed humans, animals, garments, and other deformable 3D entities. An inner-outer skeleton representation combines kinematic control with
WorldCrafter generates explorable video worlds from a single image or text prompt while preserving scenes across revisits. A jointly trained memory encoder and pose-conditioned
Mira-Scene reconstructs coherent, object-level 3D scenes from a single reference image. It jointly predicts object geometry and pixel-aligned canonical coordinates, aligning the
GAE is a geometry-native model for generating appearance and 3D structure from a shared latent representation. It compresses multi-level geometry features into a structured stat
MiMo-V2.6 is Xiaomi's natively omnimodal model family for coding, agent workflows, and visual problem solving. Pro and Flash variants are trained with scaled reinforcement learn
FixAnything repairs rendering artifacts from several kinds of 3D representation using a generalist video model. It refines degraded views from Gaussian splats, NeRFs, meshes, or
WorldSculpt reconstructs complex scenes as collections of complete object meshes that can be edited separately. It targets densely cluttered environments containing hundreds of
Lucida reconstructs indoor captures as complete, editable object assets positioned in the observed scene. It separates the work into parsing, generation, and placement, aiming t