Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids
Abstracting complex 3D shapes with parsimonious part-based representations has been a long standing goal in computer vision. This paper presents a learning-based solution to this problem which goes beyond the traditional 3D cuboid representation by exploiting superquadrics as atomic elements. We demonstrate that superquadrics lead to more expressive 3D scene parses while being easier to learn than 3D cuboid representations. Moreover, we provide an analytical solution to the Chamfer loss which avoids the need for computational expensive reinforcement learning or iterative prediction. Our model learns to parse 3D objects into consistent superquadric representations without supervision. Results on various ShapeNet categories as well as the SURREAL human body dataset demonstrate the flexibility of our model in capturing fine details and complex poses that could not have been modelled using cuboids.
Code (1)
Tasks
Reinforcement LearningSimilar Papers 제목 키워드 기반
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images
Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Inferring th…
QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction
3D occupancy prediction is crucial for robust autonomous driving systems as it enables comprehensive perception of environmental structures and semantics. Most existing methods employ dense voxel-based scene representati…
3D Semantic Occupancy PredictionAutonomous DrivingPredictionRobust Shape Fitting for 3D Scene Abstraction
Humans perceive and construct the world as an arrangement of simple parametric models. In particular, we can often describe man-made environments using volumetric primitives such as cuboids or cylinders. Inferring these …
Depth EstimationScene ParsingIm2Struct: Recovering 3D Shape Structure from a Single RGB Image
We propose to recover 3D shape structures from single RGB images, where structure refers to shape parts represented by cuboids and part relations encompassing connectivity and symmetry. Given a single 2D image with an ob…
DecoderObjectRethinking 3D Shape Generation: Diffusion over Superquadrics
Diffusion models have advanced 3D shape generation, yet most methods still denoise in high-cardinality spaces (e.g., voxel/SDF grids, meshes, or point clouds), which is computationally and memory intensive and makes it d…
Point Clouds