130 citations · 149 across the 19 of their papers we have counts for
22 papers
SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cues
Suttisak Wizadwongsa, Hyelin Nam, Supasorn Suwajanakorn +1
Generating novel renderings of a scene along user-defined camera trajectories from a single monocular video, dubbed video retaking, is a compelling but difficult problem in content…
Diffusion Mental Averages
Phonphrm Thawatdamrongkit, Sukit Seripanitkarn, Supasorn Suwajanakorn
Can a diffusion model produce its own "mental average" of a concept-one that is as sharp and realistic as a typical sample? We introduce Diffusion Mental Averages (DMA), a model-ce…
DiffSDA: Unsupervised Diffusion Sequential Disentanglement Across Modalities
Hedi Zisling, Ilan Naiman, Nimrod Berman +2
Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This rema…
Zero-shot Inexact CAD Model Alignment from a Single Image
Pattaramanee Arsomngern, Sasikarn Khwanmuang, Matthias Nießner +1
One practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image. Existin…
DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting
Worameth Chinchuthakun, Pakkapon Phongthawee, Amit Raj +3
We introduce a simple yet effective technique for estimating lighting from a single low-dynamic-range (LDR) image by reframing the task as a chrome ball inpainting problem. This ap…
Where Is The Ball: 3D Ball Trajectory Estimation From 2D Monocular Tracking
Puntawat Ponglertnapakorn, Supasorn Suwajanakorn
We present a method for 3D ball trajectory estimation from a 2D tracking sequence. To overcome the ambiguity in 3D from 2D estimation, we design an LSTM-based pipeline that utilize…
Distilling Two-Timed Flow Models by Separately Matching Initial and Terminal Velocities
Pramook Khungurn, Pratch Piyawongwisal, Sira Sriswasdi +1
A flow matching model learns a time-dependent vector field that generates a probability path that interpolates between a well-known noise dis…
Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality
Pramook Khungurn, Sukit Seripanitkarn, Phonphrm Thawatdamrongkit +1
Diffusion autoencoders (DAEs) are typically formulated as a noise prediction model and trained with a linear- noise schedule that spends much of its sampling steps at high noise…
LUSD: Localized Update Score Distillation for Text-Guided Image Editing
Worameth Chinchuthakun, Tossaporn Saengja, Nontawat Tritrong +3
While diffusion models show promising results in image editing given a target prompt, achieving both prompt fidelity and background preservation remains difficult. Recent works hav…
Optimizing Diffusion Noise Can Serve As Universal Motion Priors
Korrawe Karunratanakul, Konpat Preechakul, Emre Aksan +3
We propose Diffusion Noise Optimization (DNO), a new method that effectively leverages existing motion diffusion models as motion priors for a wide range of motion-related tasks. I…
DiffusionLight: Light Probes for Free by Painting a Chrome Ball
Pakkapon Phongthawee, Worameth Chinchuthakun, Nontaphat Sinsunthithet +4
We present a simple yet effective technique to estimate lighting in a single input image. Current techniques rely heavily on HDR panorama datasets to train neural networks to regre…
Diffusion Sampling with Momentum for Mitigating Divergence Artifacts
Suttisak Wizadwongsa, Worameth Chinchuthakun, Pramook Khungurn +2
Despite the remarkable success of diffusion models in image generation, slow sampling remains a persistent issue. To accelerate the sampling process, prior studies have reformulate…
StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer
Sasikarn Khwanmuang, Pakkapon Phongthawee, Patsorn Sangkloy +1
Our paper seeks to transfer the hairstyle of a reference image to an input photo for virtual hair try-on. We target a variety of challenges scenarios, such as transforming a long h…
Guided Motion Diffusion for Controllable Human Motion Synthesis
Korrawe Karunratanakul, Konpat Preechakul, Supasorn Suwajanakorn +1
Denoising diffusion models have shown great promise in human motion synthesis conditioned on natural language descriptions. However, integrating spatial constraints, such as pre-de…
DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadows
Puntawat Ponglertnapakorn, Nontawat Tritrong, Supasorn Suwajanakorn
We introduce a novel approach to single-view face relighting in the wild, addressing challenges such as global illumination and cast shadows. A common scheme in recent methods invo…
Zero-guidance Segmentation Using Zero Segment Labels
Pitchaporn Rewatbowornwong, Nattanat Chatthee, Ekapol Chuangsuwanich +1
CLIP has enabled new and exciting joint vision-language applications, one of which is open-vocabulary segmentation, which can locate any segment given an arbitrary text query. In o…
Accelerating Guided Diffusion Sampling with Splitting Numerical Methods
Suttisak Wizadwongsa, Supasorn Suwajanakorn
Guided diffusion is a technique for conditioning the output of a diffusion model at sampling time without retraining the network for each specific task. One drawback of diffusion m…
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
Konpat Preechakul, Nattanat Chatthee, Suttisak Wizadwongsa +1
Diffusion probabilistic models (DPMs) have achieved remarkable quality in image generation that rivals GANs'. But unlike GANs, DPMs use a set of latent variables that lack semantic…
NeX: Real-time View Synthesis with Neural Basis Expansion
Suttisak Wizadwongsa, Pakkapon Phongthawee, Jiraphon Yenphraphai +1
We present NeX, a new approach to novel view synthesis based on enhancements of multiplane image (MPI) that can reproduce next-level view-dependent effects -- in real time. Unlike…
Repurposing GANs for One-shot Semantic Part Segmentation
Nontawat Tritrong, Pitchaporn Rewatbowornwong, Supasorn Suwajanakorn
While GANs have shown success in realistic image generation, the idea of using GANs for other tasks unrelated to synthesis is underexplored. Do GANs learn meaningful structural par…
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
Supasorn Suwajanakorn, Noah Snavely, Jonathan Tompson +1
This paper presents KeypointNet, an end-to-end geometric reasoning framework to learn an optimal set of category-specific 3D keypoints, along with their detectors. Given a single i…
What Makes Kevin Spacey Look Like Kevin Spacey
Supasorn Suwajanakorn, Ira Kemelmacher-Shlizerman, Steve Seitz
We reconstruct a controllable model of a person from a large photo collection that captures his or her {\em persona}, i.e., physical appearance and behavior. The ability to operate…