Related papers: FlexGen: Flexible Multi-View Generation from Text …
Given a 3D mesh, we aim to synthesize 3D textures that correspond to arbitrary textual descriptions. Current methods for generating and assembling textures from sampled views often result in prominent seams or excessive smoothing. To tackle…
Generating flexible-view 3D scenes, including 360{\deg} rotation and zooming, from single images is challenging due to a lack of 3D data. To this end, we introduce FlexWorld, a novel framework consisting of two key components: (1) a strong…
Visual designers naturally draw inspiration from multiple visual references, combining diverse elements and aesthetic principles to create artwork. However, current image generative frameworks predominantly rely on single-source inputs --…
Texture map production is an important part of 3D modeling and determines the rendering quality. Recently, diffusion-based methods have opened a new way for texture generation. However, restricted control flexibility and limited prompt…
Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-facet controls (text and sketch), aiming to enhance the creative…
Controllable text-to-image (T2I) diffusion models generate images conditioned on both text prompts and semantic inputs of other modalities like edge maps. Nevertheless, current controllable T2I methods commonly face challenges related to…
Recent texture generation methods achieve impressive results due to the powerful generative prior they leverage from large-scale text-to-image diffusion models. However, abstract textual prompts are limited in providing global textural or…
Generating high-quality 3D content from text, single images, or sparse view images remains a challenging task with broad applications. Existing methods typically employ multi-view diffusion models to synthesize multi-view images, followed…
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…
ControlNet offers a powerful way to guide diffusion-based generative models, yet most implementations rely on ad-hoc heuristics to choose which network blocks to control-an approach that varies unpredictably with different tasks. To address…
The controllability of 3D object generation methods is achieved through input text. Existing text-to-3D object generation methods primarily focus on generating a single object based on a single object description. However, these methods…
Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllability. In this work, we propose to decompose videos into visual…
The high computational and memory requirements of large language model (LLM) inference make it feasible only with multiple high-end accelerators. Motivated by the emerging demand for latency-insensitive tasks with batched processing, this…
Despite the latest remarkable advances in generative modeling, efficient generation of high-quality 3D assets from textual prompts remains a difficult task. A key challenge lies in data scarcity: the most extensive 3D datasets encompass…
Envisioning physically plausible outcomes from a single image requires a deep understanding of the world's dynamics. To address this, we introduce PhysGen3D, a novel framework that transforms a single image into an amodal, camera-centric,…
In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion. We leverage an…
4D content generation aims to create dynamically evolving 3D content that responds to specific input objects such as images or 3D representations. Current approaches typically incorporate physical priors to animate 3D representations, but…
Controllable speech generation methods typically rely on single or fixed prompts, hindering creativity and flexibility. These limitations make it difficult to meet specific user needs in certain scenarios, such as adjusting the style while…
Deep generative models, like GANs, have considerably improved the state of the art in image synthesis, and are able to generate near photo-realistic images in structured domains such as human faces. Based on this success, recent work on…
Personalized text-to-image generation aims to seamlessly integrate specific identities into textual descriptions. However, existing training-free methods often rely on rigid visual feature injection, creating a conflict between identity…