Related papers: TOSS:High-quality Text-guided Novel View Synthesis…

We introduce TurboPortrait3D: a method for low-latency novel-view synthesis of human portraits. Our approach builds on the observation that existing image-to-3D models for portrait generation, while capable of producing renderable 3D…

We present a transformation-grounded image generation network for novel 3D view synthesis from a single image. Instead of taking a 'blank slate' approach, we first explicitly infer the parts of the geometry visible both in the input and…

Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in…

Recent advancements in text-to-video models such as Sora, Gen-3, MovieGen, and CogVideoX are pushing the boundaries of synthetic video generation, with adoption seen in fields like robotics, autonomous driving, and entertainment. As these…

Text-to-image synthesis has achieved high-quality results with recent advances in diffusion models. However, text input alone has high spatial ambiguity and limited user controllability. Most existing methods allow spatial control through…

Accurately assessing image complexity (IC) is critical for computer vision, yet most existing methods rely solely on visual features and often neglect high-level semantic information, limiting their accuracy and generalization. We introduce…

The task of novel view synthesis aims to generate unseen perspectives of an object or scene from a limited set of input images. Nevertheless, synthesizing novel views from a single image still remains a significant challenge in the realm of…

Composed Image Retrieval (CIR) is a challenging multimodal task that retrieves a target image based on a reference image and accompanying modification text. Due to the high cost of annotating CIR triplet datasets, zero-shot (ZS) CIR has…

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…

We introduce MultiDiff, a novel approach for consistent novel view synthesis of scenes from a single RGB image. The task of synthesizing novel views from a single reference image is highly ill-posed by nature, as there exist multiple,…

Pre-trained text-to-image generative models can produce diverse, semantically rich, and realistic images from natural language descriptions. Compared with language, images usually convey information with more details and less ambiguity. In…

This paper proposes a zero-shot text-to-speech (TTS) conditioned by a self-supervised speech-representation model acquired through self-supervised learning (SSL). Conventional methods with embedding vectors from x-vector or global style…

While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references,…

Generating novel views from a single image remains a challenging task due to the complexity of 3D scenes and the limited diversity in the existing multi-view datasets to train a model on. Recent research combining large-scale text-to-image…

While current emotional Text-to-Speech (TTS) models have successfully controlled verbal prosody, they often ignore non-verbal vocalizations (NVs), which are essential for authentic human emotion. Although some non-verbal datasets have…

Novel-View Human Action Synthesis aims to synthesize the movement of a body from a virtual viewpoint, given a video from a real viewpoint. We present a novel 3D reasoning to synthesize the target viewpoint. We first estimate the 3D mesh of…

Remote sensing novel view synthesis (NVS) offers significant potential for 3D interpretation of remote sensing scenes, with important applications in urban planning and environmental monitoring. However, remote sensing scenes frequently…

We introduce a scalable framework for novel view synthesis from RGB-D images with largely incomplete scene coverage. While generative neural approaches have demonstrated spectacular results on 2D images, they have not yet achieved similar…

Semantic Image Synthesis (SIS) is a subclass of image-to-image translation where a photorealistic image is synthesized from a segmentation mask. SIS has mostly been addressed as a supervised problem. However, state-of-the-art methods depend…

Recent advances in feed-forward Novel View Synthesis (NVS) have led to a divergence between two design philosophies: bias-driven methods, which rely on explicit 3D knowledge, such as handcrafted 3D representations (e.g., NeRF and 3DGS) and…