Related papers: ShapeUP: Scalable Image-Conditioned 3D Editing
The rapid advancement of pretrained text-driven diffusion models has significantly enriched applications in image generation and editing. However, as the demand for personalized content editing increases, new challenges emerge especially…
The lifting of 3D structure and camera from 2D landmarks is at the cornerstone of the entire discipline of computer vision. Traditional methods have been confined to specific rigid objects, such as those in Perspective-n-Point (PnP)…
Image spatial editing performs geometry-driven transformations, allowing precise control over object layout and camera viewpoints. Current models are insufficient for fine-grained spatial manipulations, motivating a dedicated assessment…
Editing animatable human avatars typically relies on sparse supervision, often a few edited keyframes, yet naively fitting a reconstructed avatar to these edits frequently causes identity leakage and pose-dependent temporal flicker. We…
Our work addresses limitations seen in previous approaches for object-centric editing problems, such as unrealistic results due to shape discrepancies and limited control in object replacement or insertion. To this end, we introduce…
3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. However, previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry, which is…
Recent AI-based 3D content creation has largely evolved along two paths: feed-forward image-to-3D reconstruction approaches and 3D generative models trained with 2D or 3D supervision. In this work, we show that existing feed-forward…
In this paper, we address the challenging problem of 3D toonification, which involves transferring the style of an artistic domain onto a target 3D face with stylized geometry and texture. Although fine-tuning a pre-trained 3D GAN on the…
Recent advances in flow-based generative models have enabled training-free, text-guided image editing by inverting an image into its latent noise and regenerating it under a new target conditional guidance. However, existing methods…
Goal-conditioned dynamic manipulation is inherently challenging due to complex system dynamics and stringent task constraints, particularly in deformable object scenarios characterized by high degrees of freedom and underactuation. Prior…
Recent advances in text-driven 3D scene editing and stylization, which leverage the powerful capabilities of 2D generative models, have demonstrated promising outcomes. However, challenges remain in ensuring high-quality stylization and…
Instruction-based image editing models have recently achieved impressive performance, enabling complex edits to an input image from a multi-instruction prompt. However, these models apply each instruction in the prompt with a fixed…
Data augmentation plays a crucial role in deep learning, enhancing the generalization and robustness of learning-based models. Standard approaches involve simple transformations like rotations and flips for generating extra data. However,…
Production-level workflows for producing convincing 3D dynamic human faces have long relied on an assortment of labor-intensive tools for geometry and texture generation, motion capture and rigging, and expression synthesis. Recent neural…
Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and…
We present a cascaded diffusion model based on a part-level implicit 3D representation. Our model achieves state-of-the-art generation quality and also enables part-level shape editing and manipulation without any additional training in…
Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the back view) and inaccurate shapes (e.g., animals with extra…
We present an inference-time diffusion sampling method to perform multi-view consistent image editing using pre-trained 2D image editing models. These models can independently produce high-quality edits for each image in a set of multi-view…
Face editing represents a popular research topic within the computer vision and image processing communities. While significant progress has been made recently in this area, existing solutions: (i) are still largely focused on…
Recently, 3D generative models have made impressive progress, enabling the generation of almost arbitrary 3D assets from text or image inputs. However, these approaches generate objects in isolation without any consideration for the scene…