Supplementary Material for GOTCHA

Figure 4. Challenge videos of original and deepfake samples. Each row aligns outputs against the same instance of challenge, while each column aligns the same deepfake method. This illustration also shows the driving videos of imposter.

No Challenge
Head Movement
Occlude with Hand
Manual Facial Deformation
Face Illumination with Flash
Target
Imposter
LIA
FSGAN
DFL

Figure 5. Artifacts defined for human evaluation. (a) has no deepfake artifacts, (b) has a boundary artifact near the right brow, in (c) the hand vanishes behind the face, (d) has hazy face detail, and (e) the sunglass starts vanishing briefly. Red objects indicate artifact locations..

(a) No Artifact
(b) Facial Boundary Artifacts
(c) Vanishing Object
(d) Skin Texture Inconsistency
(e) Temporal Inconsistency

Figure 12. Sample challenge images obtained using a adaptive variant of DFL trained with diverse data for long training time along with a segmentation module. As observed this version is able to do several challenges with lesser artifacts.

No Challenge
Head Movement
Occlude with Hand
Occlude with Object
Manual Deformation
Facial Illumination