Xiangjun Tang

Post doc at KAUST, PhD at State Key Lab of CAD&CG, Zhejiang University. Computer Animation, Digital Humans.

[Aymen Mir @aymenmmir]

1/5 Dropping a 3D Gaussian Splatting avatar into a captured 3DGS scene is easy. Making it cast a believable shadow is not.
Happy to share RAGA, accepted at #ECCV2026.

[Aymen Mir @aymenmmir]

5/5 Project Page at https://t.co/HaqEJ6Lt7g. Great collaboration with @peter_wonka @_JianWang_ @GerardPonsMoll1

[Xiangjun Tang @Xiangjun_Tang]

@Jaeyeon_Kim_0 @kiwhansong0 Sorry for misunderstanding. It seems that t equals to 0 for clean image. But there comes another question. For an almost clean image, the predicted score should be obvious so the conditional and unconditional prediction should be the same, but the inference diff is huge.

[Xiangjun Tang @Xiangjun_Tang]

@Jaeyeon_Kim_0 @kiwhansong0 thank you for the inspiring work! I am stuck reading fig 2. When t equals 0, the input to the network should be a pure noise. At this setting, I think the behavior of inference and training should be the same. Why score diff in training is zero but in inference is huge?