Zero-Shot Learning for the Primitives of 3D Affordance in General Objects

One of the major challenges in AI is teaching machines to precisely respond and utilize environmental functionalities, thereby achieving the affordance awareness that humans possess. Despite its importance, the field has been lagging in terms of learning, especially in 3D, as annotating affordance accompanies a laborious process due to the numerous variations of human-object interaction. The low availability of affordance data limits the learning in terms of generalization for object categories, and also simplifies the representation of affordance, capturing only a fraction of the affordance. To overcome these challenges, we propose a novel, self-supervised method to generate the 3D affordance examples given only a 3D object, without any manual annotations. The method starts by capturing the 3D object into images and creating 2D affordance images by inserting humans into the image via inpainting diffusion models, where we present the Adaptive Mask algorithm to enable human insertion without altering the original details of the object. The method consequently lifts inserted humans back to 3D to create 3D human-object pairs, where the depth ambiguity is resolved within a depth optimization framework that utilizes pre-generated human postures from multiple viewpoints. We also provide a novel affordance representation defined on relative orientations and proximity between dense human and object points, that can be easily aggregated from any 3D HOI datasets. The proposed representation serves as a primitive that can be manifested to conventional affordance representations via simple transformations, ranging from physically exerted affordances to nonphysical ones. We demonstrate the efficacy of our method and representation by generating the 3D affordance samples and deriving high-quality affordance examples from the representation, including contact, orientation, and spatial occupancies.

CHORUS: Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images

We present a method for teaching machines to understand and model the underlying spatial common sense of diverse human-object interactions in 3D in a self-supervised way. This is a challenging task, as there exist specific manifolds of the interactions that can be considered human-like and natural, but the human pose and the geometry of objects can vary even for similar interactions. Such diversity makes the annotating task of 3D interactions difficult and hard to scale, which limits the potential to reason about that in a supervised way. One way of learning the 3D spatial relationship between humans and objects during interaction is by showing multiple 2D images captured from different viewpoints when humans interact with the same type of objects. The core idea of our method is to leverage a generative model that produces high-quality 2D images from an arbitrary text prompt input as an "unbounded" data generator with effective controllability and view diversity. Despite its imperfection of the image quality over real images, we demonstrate that the synthesized images are sufficient to learn the 3D human-object spatial relations. We present multiple strategies to leverage the synthesized images, including (1) the first method to leverage a generative image model for 3D human-object spatial relation learning; (2) a framework to reason about the 3D spatial relations from inconsistent 2D cues in a self-supervised manner via 3D occupancy reasoning with pose canonicalization; (3) semantic clustering to disambiguate different types of interactions with the same object types; and (4) a novel metric to assess the quality of 3D spatial learning of interaction.

Chupa: Carving 3D Clothed Humans from Skinned Shape Priors using 2D Diffusion Probabilistic Models

We propose a 3D generation pipeline that uses diffusion models to generate realistic human digital avatars. Due to the wide variety of human identities, poses, and stochastic details, the generation of 3D human meshes has been a challenging problem. To address this, we decompose the problem into 2D normal map generation and normal map-based 3D reconstruction. Specifically, we first simultaneously generate realistic normal maps for the front and backside of a clothed human, dubbed dual normal maps, using a pose-conditional diffusion model. For 3D reconstruction, we ``carve'' the prior SMPL-X mesh to a detailed 3D mesh according to the normal maps through mesh optimization. To further enhance the high-frequency details, we present a diffusion resampling scheme on both body and facial regions, thus encouraging the generation of realistic digital avatars. We also seamlessly incorporate a recent text-to-image diffusion model to support text-based human identity control. Our method, namely, Chupa, is capable of generating realistic 3D clothed humans with better perceptual quality and identity variety.